CN113723102B - Named entity recognition method, named entity recognition device, electronic equipment and storage medium - Google Patents
Named entity recognition method, named entity recognition device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113723102B CN113723102B CN202110738499.6A CN202110738499A CN113723102B CN 113723102 B CN113723102 B CN 113723102B CN 202110738499 A CN202110738499 A CN 202110738499A CN 113723102 B CN113723102 B CN 113723102B
- Authority
- CN
- China
- Prior art keywords
- data
- model
- meaning
- sample
- enhancement
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000012545 processing Methods 0.000 claims abstract description 44
- 230000007246 mechanism Effects 0.000 claims abstract description 39
- 238000004806 packaging method and process Methods 0.000 claims abstract description 26
- 230000011218 segmentation Effects 0.000 claims description 56
- 239000011159 matrix material Substances 0.000 claims description 21
- 230000004927 fusion Effects 0.000 claims description 10
- 238000013507 mapping Methods 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 230000007547 defect Effects 0.000 abstract description 7
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 230000009286 beneficial effect Effects 0.000 abstract 1
- 238000002372 labelling Methods 0.000 description 16
- 238000003058 natural language processing Methods 0.000 description 15
- 230000008569 process Effects 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 238000007726 management method Methods 0.000 description 5
- 238000010276 construction Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012856 packing Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 238000002054 transplantation Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Machine Translation (AREA)
Abstract
The invention relates to the field of artificial intelligence and provides a named entity recognition method, which comprises the steps of firstly packaging an acquired specification statement to form a data set, then traversing the data set to form sample data, performing entity splicing processing on the sample data to form standard data, and inputting the standard data into a data enhancement model to acquire a convergence model; the data enhancement model is obtained by modifying the attention mechanism of the classical model based on NLP; and inputting the text to be annotated into the convergence model to obtain entity naming information based on the enhancement information, combining vocabulary information, n-gram information and entity information of a knowledge base when the classical model is modified in the attention mechanism, so that more priori information is beneficial to the accuracy of naming entity annotation, and the defect that a dynamic lattice structure which can only be adopted when the lattice enhancement information is utilized cannot be parallel and cannot be transplanted to other non-time sequence network results is avoided.
Description
Technical Field
The present invention relates to the field of artificial intelligence, and more particularly, to an artificial intelligence semantic recognition method, a named entity recognition device, an electronic device, and a computer readable storage medium.
Background
Named entity recognition is one of the most basic tasks of natural language processing tasks, and is one of the most important basic tasks of reading understanding, dialogue system, machine translation and the like. The most mainstream NER task model is a dictionary and a model, and most of the dictionary and the model adopt a model which is labeled by a sequence based on words, such as lstm +crf and bert+crf, but no lexical information is used in the NER task of the scheme, and the lexical information is a loss for information capture of the model; another model that utilizes lexical information, such as lattice-lstm, has the following drawbacks: the calculation speed is low, words in each sample in the dynamic structure are different, the batch matrix calculation cannot be performed, the calculation speed is low, information loss is easy to cause, each word of lattice can only obtain information of the word ending with the word, and the model can only aim at lstm time sequence networks and cannot be transplanted.
Therefore, there is a need for a named entity recognition method and device that can improve entity labeling accuracy and can perform information migration.
Disclosure of Invention
The invention provides a named entity identification method, a named entity identification device, electronic equipment and a computer readable storage medium, which can improve entity labeling precision and can carry out information transplantation, and mainly aims to solve the problems that the existing named entity identification model is low in calculation speed and easy to cause information loss.
In order to achieve the above object, the present invention provides a named entity recognition method, including:
Packaging the obtained specification sentences to form a data set;
traversing to acquire the data set to form sample data, and performing entity splicing processing on the sample data to form standard data;
Inputting the standard data into a data enhancement model to obtain a convergence model; the data enhancement model is obtained by modifying the attention mechanism of the classical model based on NLP;
And inputting the text to be annotated into the convergence model to obtain entity naming information based on the enhancement information.
Optionally, the packaging the obtained specification statement to form a data set includes:
Acquiring a sample sentence;
Extracting keywords from the sample sentences to obtain keywords;
acquiring keyword meanings of the keywords to be pre-marked;
mapping the keyword meanings with the sample sentences to obtain specification sentences;
Packaging the specification sentences to form sentence packages;
and performing data conversion on the statement package to form a data set.
Optionally, the traversing obtains the dataset to form sample data, including:
Performing traversal reading on the data set to obtain original data;
code compiling is carried out on the original data to form code data;
performing word segmentation processing on the code data to obtain a word segmentation and a corresponding position of the word segmentation;
performing secondary segmentation on the word segmentation to obtain a phrase and a corresponding position of the phrase;
uploading the word segmentation, the corresponding positions of the word segmentation, the phrase and the corresponding positions of the phrase to a knowledge base to form knowledge data;
the knowledge data is numbered to form sample data.
Optionally, the performing entity splicing processing on the sample data to form standard data includes:
According to the sample data, extracting keyword meanings corresponding to the sample data;
Expanding and splicing the sample data based on the keyword meaning to form a guessed meaning; wherein the guessed meaning includes a first meaning, a second meaning, and a third meaning;
Invoking keyword meanings of adjacent sample data of the sample data to form first-order keyword meanings, and performing expansion splicing on the first-order keyword meanings to form first-order guess meanings;
Acquiring next sample data of the adjacent sample data to form second-order keyword meanings, and performing expansion and splicing on the second-order keyword meanings to form second-order guess meanings;
Selecting one guess meaning from the first meaning, the second meaning and the third meaning based on the first-order guess meaning and the second-order guess meaning according to a semantic coordination algorithm as a sample meaning of the sample data;
and splicing the sample semantics in the sample data to finish entity splicing processing to form standard data.
Optionally, the inputting the standard data into the data enhancement model to obtain the convergence model includes:
Forming a basic model by adopting an NLP classical model structure;
modifying the attention mechanism of the basic model to obtain a data enhancement model;
inputting the standard data into the data enhancement model so that the data enhancement model obtains a prediction tag according to knowledge data in the standard data, and calculating lost data according to the preset tag and the sample semantics;
And the lost data is returned to the data enhancement model to adjust parameters of the data enhancement model according to the lost data until the data enhancement model converges to obtain a convergence model.
Optionally, the modifying the attention mechanism of the base model to obtain a data enhancement model includes:
Acquiring the relative position between two input span according to the input span position of the basic model;
Acquiring a relative matrix according to the relative position;
Fusing the relative positions of the two input span based on the relative matrix to obtain a fusion matrix;
calculating the original self-attention based on the fusion matrix;
Calculating an attention mechanism of content-content based on the original self-attention, and simultaneously calculating an attention mechanism of content-location to form a data enhancement layer;
and fusing and unifying the data enhancement layer and the basic model to form a data enhancement model.
Optionally, the inputting the text to be annotated into the convergence model to obtain entity naming information based on the enhancement information includes:
Inputting a text to be annotated into the convergence model so that the annotated text generates basic data through the basic model;
performing enhancement processing on the basic data through the data enhancement layer to form data enhancement information;
And acquiring entity naming information aiming at the text to be annotated based on the data enhancement information.
In order to solve the above problems, the present invention further provides a named entity recognition device, which includes:
the data packaging unit is used for packaging the acquired specification sentences to form a data set;
The entity splicing unit is used for traversing and acquiring the data set to form sample data, and carrying out entity splicing processing on the sample data to form standard data;
The model transformation unit is used for inputting the standard data into a data enhancement model to obtain a convergence model; the data enhancement model is obtained by modifying the attention mechanism of the classical model based on NLP;
And the entity naming unit is used for inputting the text to be annotated into the convergence model to obtain entity naming information based on the enhancement information.
In order to solve the above-mentioned problems, the present invention also provides an electronic apparatus including:
A memory storing at least one instruction; and
And the processor executes the instructions stored in the memory to realize the steps in the named entity identification method.
In order to solve the above-mentioned problems, the present invention also provides a computer-readable storage medium having stored therein at least one instruction that is executed by a processor in an electronic device to implement the named entity recognition method described above.
Firstly, packaging an acquired specification statement to form a data set, traversing the data set to form sample data, performing entity splicing processing on the sample data to form standard data, and inputting the standard data into a data enhancement model to acquire a convergence model; the data enhancement model is obtained by modifying the attention mechanism of the classical model based on NLP; and inputting the text to be annotated into the convergence model to obtain entity naming information based on the enhancement information, combining vocabulary information, n-gram information and entity information of a knowledge base when the classical model is modified in a attentive mechanism, so that more priori information is helpful for naming entity annotation precision, expanding and utilizing the enhancement information on the basis that the classical model only utilizes vocabulary, and avoiding the defects that dynamic lattice structures which can only be adopted when the lattice enhancement information is utilized cannot be parallel and cannot be transplanted to other non-time sequence network results.
Drawings
FIG. 1 is a flowchart illustrating a named entity recognition method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a named entity recognition device according to an embodiment of the present invention;
Fig. 3 is a schematic diagram of an internal structure of an electronic device for implementing a named entity recognition method according to an embodiment of the present invention;
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Most models adopt a model of lstm +crf, bert +crf based on word sequence labeling, but no lexical information is used in the NER task of the scheme, which is a loss for information capture of the model, and the latest model using lexical information such as lattice-lstm has the following defects:
1. The calculation speed is slow: the dynamic structure (different words in each sample) cannot be used for batch matrix calculation, and the calculation speed is low;
2. Information loss: each word in the lattice-lstm model can only obtain information of words ending with that word and cannot be transplanted, and such a model can only be more restrictive for such timing networks as lstm.
In order to solve the above problems, the present invention provides a named entity recognition method. Referring to fig. 1, a flow chart of a named entity recognition method according to an embodiment of the invention is shown. The method may be performed by an apparatus, which may be implemented in software and/or hardware.
In this embodiment, the named entity recognition method includes:
s1: packaging the obtained specification sentences to form a data set;
s2: traversing to acquire the data set to form sample data, and performing entity splicing processing on the sample data to form standard data;
s3: inputting the standard data into a data enhancement model to obtain a convergence model; the data enhancement model is obtained by modifying the attention mechanism of the classical model based on NLP;
S4: and inputting the text to be annotated into the convergence model to obtain entity naming information based on the enhancement information.
In the embodiment shown in fig. 1, step S1 is a process of packaging the obtained specification sentence to form a data set, where the step of packaging the obtained specification sentence to form the data set includes:
S11: acquiring a sample sentence;
s12: extracting keywords from the sample sentences to obtain keywords;
s13: acquiring keyword meanings of the keywords to be pre-marked;
S14: mapping the keyword meanings with the sample sentences to obtain specification sentences;
s15: packaging the specification sentences to form sentence packages;
S16: performing data conversion on the statement package to form a data set;
specifically, the sample data may be a series of commonly used sentences or phrases, in this embodiment, an urban construction system is taken as an example, and the sample sentences may be sentences about urban construction, smart cities and smart spaces;
The steps S12 and S13 are processes of extracting keywords from the sample data, that is, obtain the keywords in the sample sentence, for example, if the sample sentence is "no more intense than the sun on the first building today", the step S12 is extracting the time keyword "today", the place keyword "first building" and the adjective keyword "fierce", meanwhile, the meaning represented by the keyword is annotated by the step S13, and a specific labeling manner is not limited, in this embodiment, the meaning is specific meaning of time, place, character, cause, pass, result, adjective, and the like, and pre-labeling is pre-labeling, that is, storing the meaning of the keyword and the keyword together, in other words, describing the meaning of the keyword in text language, storing the described sentence together with the keyword, and the specific labeling manner can be manually or by any tool capable of labeling and marking the meaning of the keyword, which is not described herein;
In step S14, the process of mapping the meaning of the keyword with the sample data is that in brief step S13 may be used as the mapping of the meaning of the keyword to the keyword, step S14 establishes the mapping of the meaning of the keyword with the sample data, thereby forming the corresponding relationship between the meaning of the keyword and the sample data, that is, establishes the corresponding relationship between the sample data and the meaning of the keyword, inputs the corresponding relationship into the convolutional neural network for repeated training, so that the trained neural network can automatically obtain the meaning of the keyword corresponding to the sample data according to the sample data, and step S14 lays a foundation for forming standard data in the later period and inputting the standard data into the data enhancement model to obtain the convergence model.
In the embodiment shown in fig. 1, step S2 includes S21: traversing to obtain the dataset to form sample data; s22: performing entity splicing processing on the sample data to form standard data; wherein traversing the step of acquiring the data set to form sample data comprises:
S211: performing traversal reading on the data set to acquire original data;
s212: code compiling is carried out on the original data to form code data;
s213: performing word segmentation processing on the code data to obtain a word segmentation and a corresponding position of the word segmentation;
S214: performing secondary segmentation on the word segmentation to obtain a phrase and a corresponding position of the phrase;
S215: uploading the word segmentation, the corresponding position of the word segmentation, the phrase and the corresponding position of the phrase to a knowledge base to form knowledge data;
S216: the knowledge data is numbered to form sample data.
Performing entity splicing processing on the sample data to form standard data, wherein the entity splicing processing comprises the following steps:
s221: according to the sample data, extracting keyword meanings corresponding to the sample data;
S222: expanding and splicing the sample data based on the keyword meaning to form a guessed meaning; wherein the guessed meaning includes a first meaning, a second meaning, and a third meaning;
S223: invoking keyword meanings of adjacent sample data of the sample data to form first-order keyword meanings, and performing expansion splicing on the first-order keyword meanings to form first-order guess meanings; wherein the first-order guessing meaning comprises a first-order first meaning, a first-order second meaning and a first-order third meaning;
s224: acquiring next sample data of the adjacent sample data to form second-order keyword meanings, and performing expansion and splicing on the second-order keyword meanings to form second-order guess meanings; wherein the second order guessed meaning includes a second order first meaning, a second order second meaning, and a second order third meaning;
S225: selecting one guess meaning from the first meaning, the second meaning and the third meaning based on the first-order guess meaning and the second-order guess meaning according to a semantic coordination algorithm as a sample meaning of the sample data;
s226: splicing the sample semantics in the sample data to finish entity splicing processing to form standard data;
In this way, standard data is formed, it should be noted that, after one sample data generates standard data, the adjacent sample data and the next sample data mentioned in step S223 and step S224 are sequentially used as sample data to obtain sample semantics about the adjacent sample data and the next sample data.
Specifically, in step S213, the word segmentation tool performs word segmentation processing on the code data to obtainAnd corresponding position/>Wherein/>Is the position of the last word of the i-th word in si; i.e.
In step S214, the second segmentation is not just a second segmentation, but a second type segmentation, i.e., segmentation of the word into phrases, is performed, and the number of times of segmentation is not particularly limited, specifically, as follows:
dividing sentences into 2 grams to obtain phrase fragments and corresponding positions, namely
In this embodiment, the second division further includes an n-1 th second division, i.e., ngram division (n-th division), and the divided segments are matched in the knowledge base to obtain the matched entity, and the position is marked
So as to obtain the corresponding positions of the phrases and the phrases;
steps S221 to S223 are processes of acquiring sample data, sample data next, and a guess meaning of the next data of the sample data, and the adjacent sample data and the next sample data of the adjacent sample data in steps S223, S224 acquire sample semantics at auxiliary sample data, and then the "adjacent sample data" is taken as sample data again, the "next sample data of the adjacent sample data" is taken as adjacent sample data again, and so on, to acquire sample semantics of each sample data.
In the embodiment shown in fig. 1, step S3 is to input the standard data into a data enhancement model to obtain a convergence model; the data enhancement model is obtained by modifying the attention mechanism of the classical model based on NLP; the step of inputting the standard data into the data enhancement model to obtain a convergence model includes:
S31: forming a basic model by adopting an NLP classical model structure; wherein the basic model is a transducer structure;
S32: modifying the attention mechanism of the basic model to obtain a data enhancement model;
S33: inputting the standard data into the data enhancement model so that the data enhancement model obtains a prediction tag according to knowledge data in the standard data, and calculating lost data according to the preset tag and the sample semantics;
s34: and the lost data is returned to the data enhancement model to adjust the parameters of the data enhancement model according to the lost data until the data enhancement model converges to obtain a convergence model.
Wherein modifying the attention mechanism of the base model to obtain the data enhancement model comprises:
s321: acquiring the relative position between two input span according to the input span position of the basic model;
S322: acquiring a relative matrix according to the relative position;
S323: fusing the relative positions of the two input span based on the relative matrix to obtain a fusion matrix;
S324: calculating the original self-attention based on the fusion matrix;
S325: calculating an attention mechanism of content-content based on the original self-attention, and simultaneously calculating an attention mechanism of content-location to form a data enhancement layer;
s326: and fusing and unifying the data enhancement layer and the basic model to form a data enhancement model.
Specifically, in step S31, the base model P is:
p＝softmax(transformer([sinput,li-sta,li-end])))
y′＝agmax(p)
The loss is BEloss
loss＝BEloss(y，y′)
When the basic model is trained, the loss returns model parameter update, and model training is completed after convergence;
In step S32, the process of obtaining the data enhancement model is a process of modifying the transformation structure, that is, the principle of lattice-lstm (remark: mesh long and short memory time sequence network, a deep learning network structure) is used, on the basis of the principle of lattice (remark: a network structure for expanding and connecting words in sentences), the original words are expanded by lattice information and then are input as a model by combining n-gram information and entity knowledge base information, a transformation basic structure is adopted on the model structure, and the transformation structure is designed to better utilize the enhanced vocabulary information for vocabulary enhancement attention modification, thereby labeling the named entities.
In this embodiment, a specific implementation manner is as follows, where data input is performed first,
input＝[sinput,lstart,lend]
Input is coded by embedding
Oemb＝Embedding(sinput)+PosEmbeding(lstart,lend)
The k x d output matrix k to obtain O emb＝[e1,e2...ed is the length of the sentence and d is the length of embedding vec;
the conventional transducer structure is that in which e q,ek,ev is the result of embedding in O emb on a certain span, respectively
[Q，K，V]＝[eq,ek,ev]
Att(A，V)＝softamx(A)V
In this embodiment, the relative position is first calculated from the span position in the input,Is the distance between the start positions of the ith span and the jth span,/>Is the distance between the actual position of the ith span and the end position of the jth span, yielding 4 matrices [ d ss,dst,dtt,dts ]:
Then fusing the relative positions of the span of the two positions
And attention of content-location needs to be calculated in addition to attention of content-content based on original self-attention
Wherein,Attention for content-to-content and content-to-location, respectively, μ TEjWk,E+vTRijWk,R are their biasing terms
Similar to self-attention later
Att(A，V)＝softamx(A*)V
Followed by a conventional transducer module:
Otemp＝Norm(Att(A,V)+Oemb)
y～＝ngmax(softmax(Norm(Otemp+NN(Otemp))))
the obtained predictive label and the real label find loss, model adjustment parameters are returned, and the model is obtained after convergence
loss＝BEloss(y,y′)。
In the embodiment shown in fig. 1, step S4 is to input the text to be annotated into the convergence model to obtain entity naming information based on the enhancement information; the step of inputting the text to be annotated into the convergence model to obtain the entity naming information based on the enhancement information comprises the following steps:
s41: inputting a text to be annotated into the convergence model so that the annotated text generates basic data through the basic model;
s42: performing enhancement processing on the basic data through the data enhancement layer to form data enhancement information;
S43: and acquiring entity naming information aiming at the text to be annotated based on the data enhancement information.
Specifically, the step S41 is a basic information model generated according to a training model, in the conventional technology, the entity naming information is directly generated through the basic model, but the accuracy is not high, so in this embodiment, the method further includes a step S42, in which the basic data is subjected to data enhancement processing through the improved data enhancement model in the step S32, that is, the data enhancement model is reformed by attention, so that enhanced lexical information can be better utilized, thereby labeling the named entities, and further enhancing the accuracy and precision of entity naming labeling;
In the step S43, the entity naming information is label information in the embodiment, that is, the convergence model automatically generates a prediction label for the text to be marked, and the accuracy of the prediction label is nearly accurate, so that based on vocabulary information, n-gram information, entity information of a knowledge base, more priori information is helpful to the accuracy of naming entity marking, and enhancement information is developed and utilized based on the fact that the traditional NER task only utilizes vocabulary, so that the defects that dynamic lattice structure which can only be adopted when the enhancement information is utilized cannot be parallel and cannot be transplanted to other non-time-sequence network results are overcome.
The named entity identification method provided by the invention comprises the steps of firstly packaging an acquired specification statement to form a data set, then traversing the data set to form sample data, performing entity splicing processing on the sample data to form standard data, and inputting the standard data into a data enhancement model to acquire a convergence model; the data enhancement model is obtained by modifying the attention mechanism of the classical model based on NLP; and inputting the text to be annotated into the convergence model to obtain entity naming information based on the enhancement information, combining vocabulary information, n-gram information and entity information of a knowledge base when the classical model is modified in a attentive mechanism, so that more priori information is helpful for naming entity annotation precision, expanding and utilizing the enhancement information on the basis that the classical model only utilizes vocabulary, and avoiding the defects that dynamic lattice structures which can only be adopted when the lattice enhancement information is utilized cannot be parallel and cannot be transplanted to other non-time sequence network results.
As described above, in the embodiment shown in FIG. 1, the named entity recognition method provided by the present invention has the following advantages: ① Performing word segmentation processing on the code data to obtain word segmentation and corresponding positions of the word segmentation, performing secondary segmentation on the word segmentation to obtain word groups and corresponding positions of the word groups, and uploading the word segmentation and the corresponding positions of the word segmentation, the word groups and the corresponding positions of the word groups to a knowledge base to form knowledge data, so that complete word group-semantic mapping can be formed in the data only, and a foundation is laid for accurate labeling; ② Selecting one guess meaning from the first meaning, the second meaning and the third meaning as sample meaning of sample data according to a semantic coordination algorithm based on the first-order guess meaning and the second-order guess meaning, sequentially taking adjacent sample data and next sample data as sample data to obtain sample meaning related to the adjacent sample data and the next sample data, namely determining the sample meaning according to the meaning of data adjacent to the sample data, and circularly and repeatedly determining the sample meaning of each sample data; ③ And calculating the original self-attention based on the fusion matrix, calculating the attention mechanism of content-content based on the original self-attention, simultaneously calculating the attention mechanism of content-location to form a data enhancement layer, and fusing and unifying the data enhancement layer and the basic model to form a data enhancement model, thereby improving the labeling precision of the whole convergence model.
As shown in fig. 2, the present invention provides a named entity recognition device 100, which may be installed in an electronic apparatus. Depending on the implemented functionality, the named entity recognition means 100 may comprise a data packaging unit 101, an entity stitching unit 102, a model transformation unit 103, and an entity naming unit 104. The module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.
In the present embodiment, the functions concerning the respective modules/units are as follows:
A data packaging unit 101 for packaging the obtained specification statement to form a data set;
The entity splicing unit 102 is used for traversing and acquiring the data set to form sample data, and performing entity splicing processing on the sample data to form standard data;
A model modification unit 103 for inputting the standard data into a data enhancement model to obtain a convergence model; the data enhancement model is obtained by modifying the attention mechanism of the classical model based on NLP;
And the entity naming unit 104 is used for inputting the text to be annotated into the convergence model to obtain entity naming information based on the enhancement information.
Wherein the step of the data packing unit 101 packing the acquired specification sentence to form a data set includes:
Acquiring a sample sentence;
Extracting keywords from the sample sentences to obtain keywords;
acquiring keyword meanings of the keywords to be pre-marked;
mapping the keyword meanings with the sample sentences to obtain specification sentences;
Packaging the specification sentences to form sentence packages;
and performing data conversion on the statement package to form a data set.
Specifically, the sample data may be a series of commonly used sentences or phrases, in this embodiment, an urban construction system is taken as an example, and the sample sentences may be sentences about urban construction, smart cities and smart spaces;
The process of extracting the keywords from the sample data can obtain the keywords in the sample sentence, for example, if the sample sentence is "no more intense than the sun on the first building today", the time keywords are extracted "today", the place keywords are "the first building" and adjective keywords are "intense", and meanwhile, the meaning represented by the keywords is noted, and the specific labeling mode is not limited, and in this embodiment, the meaning is specific meaning such as time, place, person, cause, pass, result, adjective, and the like.
The entity splicing unit 102 is used for traversing the acquired data set to form sample data, and performing entity splicing processing on the sample data to form standard data; wherein traversing the step of acquiring the data set to form sample data comprises:
Performing traversal reading on the data set to acquire original data;
Code compiling is carried out on the original data to form code data;
Performing word segmentation processing on the code data to obtain a word segmentation and a corresponding position of the word segmentation;
performing secondary segmentation on the word segmentation to obtain a phrase and a corresponding position of the phrase;
Uploading the word segmentation, the corresponding position of the word segmentation, the phrase and the corresponding position of the phrase to a knowledge base to form knowledge data;
Numbering the knowledge data to form sample data;
Performing entity splicing processing on the sample data to form standard data, wherein the entity splicing processing comprises the following steps:
According to the sample data, extracting keyword meanings corresponding to the sample data;
Expanding and splicing the sample data based on the keyword meaning to form a guessed meaning; wherein the guessed meaning includes a first meaning, a second meaning, and a third meaning;
Invoking keyword meanings of adjacent sample data of the sample data to form first-order keyword meanings, and performing expansion splicing on the first-order keyword meanings to form first-order guess meanings; wherein the first-order guessing meaning comprises a first-order first meaning, a first-order second meaning and a first-order third meaning;
Acquiring next sample data of the adjacent sample data to form second-order keyword meanings, and performing expansion and splicing on the second-order keyword meanings to form second-order guess meanings; wherein the second order guessed meaning includes a second order first meaning, a second order second meaning, and a second order third meaning;
Selecting one guess meaning from the first meaning, the second meaning and the third meaning based on the first-order guess meaning and the second-order guess meaning according to a semantic coordination algorithm as a sample meaning of the sample data;
and splicing the sample semantics in the sample data to finish entity splicing processing to form standard data.
In this way, standard data is formed, and after one sample data generates standard data, adjacent sample data and the next sample data are sequentially used as sample data to obtain sample semantics about the adjacent sample data and the next sample data.
A model modification unit 103 for inputting the standard data into the data enhancement model to obtain a convergence model; the data enhancement model is obtained by modifying the attention mechanism of the classical model based on NLP; the step of inputting the standard data into the data enhancement model to obtain a convergence model includes:
Forming a basic model by adopting an NLP classical model structure; wherein the basic model is a transducer structure;
Modifying the attention mechanism of the basic model to obtain a data enhancement model;
inputting the standard data into the data enhancement model so that the data enhancement model obtains a prediction tag according to knowledge data in the standard data, and calculating lost data according to the preset tag and the sample semantics;
And the lost data is returned to the data enhancement model to adjust the parameters of the data enhancement model according to the lost data until the data enhancement model converges to obtain a convergence model.
Wherein modifying the attention mechanism of the base model to obtain the data enhancement model comprises:
Acquiring the relative position between two input span according to the input span position of the basic model;
Acquiring a relative matrix according to the relative position;
fusing the relative positions of the two input span based on the relative matrix to obtain a fusion matrix;
Calculating the original self-attention based on the fusion matrix;
calculating an attention mechanism of content-content based on the original self-attention, and simultaneously calculating an attention mechanism of content-location to form a data enhancement layer;
and fusing and unifying the data enhancement layer and the basic model to form a data enhancement model.
The entity naming unit 104 is configured to input a text to be annotated into the convergence model to obtain entity naming information based on the enhancement information; the step of inputting the text to be annotated into the convergence model to obtain the entity naming information based on the enhancement information comprises the following steps:
inputting a text to be annotated into the convergence model so that the annotated text generates basic data through the basic model;
performing enhancement processing on the basic data through the data enhancement layer to form data enhancement information;
And acquiring entity naming information aiming at the text to be annotated based on the data enhancement information.
Specifically, in the conventional technology, the entity naming information is directly generated through the basic model, but the accuracy is not high, so that the embodiment further comprises a step of enhancing the basic data through the data enhancement layer to form data enhancement information, wherein the step is to perform data enhancement processing on the basic data through the improved data enhancement model, namely, the data enhancement model is subjected to attention transformation, so that enhanced vocabulary information can be better utilized, and therefore named entities are marked, and the accuracy of entity naming marking are enhanced.
In addition, the entity naming information is label information in the embodiment, namely, the convergence model automatically generates a prediction label aiming at the text to be marked, and the precision of the prediction label is nearly accurate, so that based on vocabulary information, n-gram information and entity information of a knowledge base, more priori information is helpful for naming the precision of entity marking, and the enhancement information is developed and utilized on the basis that the traditional NER task only utilizes vocabulary, so that the defects that a dynamic lattice structure which can only be adopted when the enhancement information is utilized cannot be parallel and cannot be transplanted to other non-time sequence network results are overcome.
As described above, in the named entity recognition device 100 provided by the present invention, firstly, the data packaging unit 101 packages the obtained specification sentence to form a data set, then the entity splicing unit 102 traverses to obtain the data set to form sample data, and performs entity splicing processing on the sample data to form standard data, and then the model transformation unit 103 inputs the standard data into the data enhancement model to obtain a convergence model; the data enhancement model is obtained by modifying the attention mechanism of the classical model based on NLP; the entity naming unit 104 is used for inputting the text to be annotated into the convergence model to obtain entity naming information based on the enhancement information, and when the classical model is modified by the attention mechanism, vocabulary information, n-gram information and entity information of a knowledge base are combined, so that more priori information is helpful for the accuracy of naming entity annotation, enhancement information is utilized by expanding on the basis that the classical model only utilizes vocabulary, and the defects that dynamic lattice structures which can only be adopted when the enhancement information is utilized cannot be parallel and cannot be transplanted to other non-time sequence network results are overcome.
The named entity recognition device provided by the invention has the following advantages: ① Performing word segmentation processing on the code data to obtain word segmentation and corresponding positions of the word segmentation, performing secondary segmentation on the word segmentation to obtain word groups and corresponding positions of the word groups, and uploading the word segmentation and the corresponding positions of the word segmentation, the word groups and the corresponding positions of the word groups to a knowledge base to form knowledge data, so that complete word group-semantic mapping can be formed in the data only, and a foundation is laid for accurate labeling; ② Selecting one guess meaning from the first meaning, the second meaning and the third meaning as sample meaning of sample data according to a semantic coordination algorithm based on the first-order guess meaning and the second-order guess meaning, sequentially taking adjacent sample data and next sample data as sample data to obtain sample meaning related to the adjacent sample data and the next sample data, namely determining the sample meaning according to the meaning of data adjacent to the sample data, and circularly and repeatedly determining the sample meaning of each sample data; ③ And calculating the original self-attention based on the fusion matrix, calculating the attention mechanism of content-content based on the original self-attention, simultaneously calculating the attention mechanism of content-location to form a data enhancement layer, and fusing and unifying the data enhancement layer and the basic model to form a data enhancement model, thereby improving the labeling precision of the whole convergence model.
As shown in fig. 3, the present invention provides an electronic device 1 of a named entity recognition method.
The electronic device 1 may comprise a processor 10, a memory 11 and a bus, and may further comprise a computer program, such as a named entity recognition program 12, stored in the memory 11 and executable on said processor 10.
The memory 11 includes at least one type of readable storage medium, including flash memory, a mobile hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device 1, such as a removable hard disk of the electronic device 1. The memory 11 may in other embodiments also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD) or the like, which are provided on the electronic device 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 may be used not only for storing application software installed in the electronic device 1 and various types of data, such as codes of named entity recognition programs, but also for temporarily storing data that has been output or is to be output.
The processor 10 may be comprised of integrated circuits in some embodiments, for example, a single packaged integrated circuit, or may be comprised of multiple integrated circuits packaged with the same or different functions, including one or more central processing units (Central Processing unit, CPU), microprocessors, digital processing chips, graphics processors, combinations of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the entire electronic device using various interfaces and lines, executes or executes programs or modules (e.g., named entity recognition programs, etc.) stored in the memory 11, and invokes data stored in the memory 11 to perform various functions of the electronic device 1 and process data.
The bus may be a peripheral component interconnect standard (PERIPHERAL COMPONENT INTERCONNECT, PCI) bus, or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. The bus is arranged to enable a connection communication between the memory 11 and at least one processor 10 etc.
Fig. 3 shows only an electronic device with components, it being understood by a person skilled in the art that the structure shown in fig. 3 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or may combine certain components, or may be arranged in different components.
For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for supplying power to each component, and preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management, and the like are implemented through the power management device. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure detection circuit, power converter or inverter, power status indicator, etc. The electronic device 1 may further include various sensors, bluetooth modules, wi-Fi modules, etc., which will not be described herein.
Further, the electronic device 1 may also comprise a network interface, optionally the network interface may comprise a wired interface and/or a wireless interface (e.g. WI-FI interface, bluetooth interface, etc.), typically used for establishing a communication connection between the electronic device 1 and other electronic devices.
The electronic device 1 may optionally further comprise a user interface, which may be a Display, an input unit, such as a Keyboard (Keyboard), or a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device 1 and for displaying a visual user interface.
It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.
The named entity recognition program 12 stored in the memory 11 of the electronic device 1 is a combination of instructions that, when executed in the processor 10, may implement:
Packaging the obtained specification sentences to form a data set;
Traversing to acquire the data set to form sample data, and performing entity splicing processing on the sample data to form standard data;
inputting the standard data into a data enhancement model to obtain a convergence model; the data enhancement model is obtained by modifying the attention mechanism of the classical model based on NLP;
and inputting the text to be annotated into the convergence model to obtain entity naming information based on the enhancement information.
Specifically, the specific implementation method of the above instructions by the processor 10 may refer to the description of the relevant steps in the corresponding embodiment of fig. 1, which is not repeated herein. It should be emphasized that, to further ensure the privacy and security of the named entity identification, the named entity identification data is stored in the node of the blockchain where the server cluster is located.
Further, the modules/units integrated in the electronic device 1 may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as separate products. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM).
Embodiments of the present invention also provide a computer readable storage medium, which may be non-volatile or volatile, storing a computer program which when executed by a processor implements:
Packaging the obtained specification sentences to form a data set;
Traversing to acquire the data set to form sample data, and performing entity splicing processing on the sample data to form standard data;
inputting the standard data into a data enhancement model to obtain a convergence model; the data enhancement model is obtained by modifying the attention mechanism of the classical model based on NLP;
and inputting the text to be annotated into the convergence model to obtain entity naming information based on the enhancement information.
In particular, the specific implementation method of the computer program when executed by the processor may refer to descriptions of related steps in the named entity recognition method of the embodiment, which are not described herein.
In the several embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The blockchain (Blockchain), essentially a de-centralized database, is a string of data blocks that are generated in association using cryptographic methods, each of which contains information from a batch of network transactions for verifying the validity (anti-counterfeit) of its information and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. A plurality of units or means recited in the system claims can also be implemented by means of software or hardware by means of one unit or means. The terms second, etc. are used to denote a name, but not any particular order.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (7)
1. A named entity recognition method, comprising:
Packaging the obtained specification sentences to form a data set; the packaging the obtained specification statement to form a data set includes: acquiring a sample sentence; extracting keywords from the sample sentences to obtain keywords; acquiring keyword meanings of the keywords to be pre-marked; mapping the keyword meanings with the sample sentences to obtain specification sentences; packaging the specification sentences to form sentence packages; performing data conversion on the statement package to form a data set;
Traversing to acquire the data set to form sample data, and performing entity splicing processing on the sample data to form standard data; wherein the traversing obtains the data set to form sample data, comprising: performing traversal reading on the data set to obtain original data; code compiling is carried out on the original data to form code data; performing word segmentation processing on the code data to obtain a word segmentation and a corresponding position of the word segmentation; performing secondary segmentation on the word segmentation to obtain a phrase and a corresponding position of the phrase; uploading the word segmentation, the corresponding positions of the word segmentation, the phrase and the corresponding positions of the phrase to a knowledge base to form knowledge data; numbering the knowledge data to form sample data; the entity splicing processing is performed on the sample data to form standard data, including: according to the sample data, extracting keyword meanings corresponding to the sample data; expanding and splicing the sample data based on the keyword meaning to form a guessed meaning; wherein the guessed meaning includes a first meaning, a second meaning, and a third meaning; invoking keyword meanings of adjacent sample data of the sample data to form first-order keyword meanings, and performing expansion splicing on the first-order keyword meanings to form first-order guess meanings; acquiring next sample data of the adjacent sample data to form second-order keyword meanings, and performing expansion and splicing on the second-order keyword meanings to form second-order guess meanings; selecting one guess meaning from the first meaning, the second meaning and the third meaning based on the first-order guess meaning and the second-order guess meaning according to a semantic coordination algorithm as a sample meaning of the sample data; splicing the sample semantics in the sample data to finish entity splicing processing to form standard data;
Inputting the standard data into a data enhancement model to obtain a convergence model; the data enhancement model is obtained by modifying the attention mechanism of the classical model based on NLP;
And inputting the text to be annotated into the convergence model to obtain entity naming information based on the enhancement information.
2. The named entity recognition method of claim 1, wherein said inputting the standard data into a data enhancement model to obtain a convergence model comprises:
Forming a basic model by adopting an NLP classical model structure;
modifying the attention mechanism of the basic model to obtain a data enhancement model;
Inputting the standard data into the data enhancement model so that the data enhancement model obtains a prediction tag according to knowledge data in the standard data, and calculating lost data according to the prediction tag and the sample semantics;
And the lost data is returned to the data enhancement model to adjust parameters of the data enhancement model according to the lost data until the data enhancement model converges to obtain a convergence model.
3. The named entity recognition method of claim 2, wherein said adapting the attention mechanism of the base model to obtain a data enhancement model comprises:
acquiring the relative position between two input span according to the input span position of the basic model;
Acquiring a relative matrix according to the relative position;
Fusing the relative positions of the two input span based on the relative matrix to obtain a fusion matrix;
Calculating an original self-attention based on the fusion matrix;
Calculating an attention mechanism of content-content based on the original self-attention, and simultaneously calculating an attention mechanism of content-location to form a data enhancement layer;
and fusing and unifying the data enhancement layer and the basic model to form a data enhancement model.
4. The named entity recognition method of claim 3, wherein said entering text to be annotated into the convergence model to obtain enhanced information based entity naming information comprises:
Inputting a text to be annotated into the convergence model so that the annotated text generates basic data through the basic model;
performing enhancement processing on the basic data through the data enhancement layer to form data enhancement information;
And acquiring entity naming information aiming at the text to be annotated based on the data enhancement information.
5. A named entity recognition device, the device comprising:
the data packaging unit is used for packaging the acquired specification sentences to form a data set; the packaging the obtained specification statement to form a data set includes: acquiring a sample sentence; extracting keywords from the sample sentences to obtain keywords; acquiring keyword meanings of the keywords to be pre-marked; mapping the keyword meanings with the sample sentences to obtain specification sentences; packaging the specification sentences to form sentence packages; performing data conversion on the statement package to form a data set;
The entity splicing unit is used for traversing and acquiring the data set to form sample data, and carrying out entity splicing processing on the sample data to form standard data; wherein the traversing obtains the data set to form sample data, comprising: performing traversal reading on the data set to obtain original data; code compiling is carried out on the original data to form code data; performing word segmentation processing on the code data to obtain a word segmentation and a corresponding position of the word segmentation; performing secondary segmentation on the word segmentation to obtain a phrase and a corresponding position of the phrase; uploading the word segmentation, the corresponding positions of the word segmentation, the phrase and the corresponding positions of the phrase to a knowledge base to form knowledge data; numbering the knowledge data to form sample data; the entity splicing processing is performed on the sample data to form standard data, including: according to the sample data, extracting keyword meanings corresponding to the sample data; expanding and splicing the sample data based on the keyword meaning to form a guessed meaning; wherein the guessed meaning includes a first meaning, a second meaning, and a third meaning; invoking keyword meanings of adjacent sample data of the sample data to form first-order keyword meanings, and performing expansion splicing on the first-order keyword meanings to form first-order guess meanings; acquiring next sample data of the adjacent sample data to form second-order keyword meanings, and performing expansion and splicing on the second-order keyword meanings to form second-order guess meanings; selecting one guess meaning from the first meaning, the second meaning and the third meaning based on the first-order guess meaning and the second-order guess meaning according to a semantic coordination algorithm as a sample meaning of the sample data; splicing the sample semantics in the sample data to finish entity splicing processing to form standard data;
The model transformation unit is used for inputting the standard data into a data enhancement model to obtain a convergence model; the data enhancement model is obtained by modifying the attention mechanism of the classical model based on NLP;
And the entity naming unit is used for inputting the text to be annotated into the convergence model to obtain entity naming information based on the enhancement information.
6. An electronic device, the electronic device comprising:
At least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the steps in the named entity recognition method of any one of claims 1 to 4.
7. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the named entity recognition method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110738499.6A CN113723102B (en) | 2021-06-30 | 2021-06-30 | Named entity recognition method, named entity recognition device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110738499.6A CN113723102B (en) | 2021-06-30 | 2021-06-30 | Named entity recognition method, named entity recognition device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113723102A CN113723102A (en) | 2021-11-30 |
| CN113723102B true CN113723102B (en) | 2024-04-26 |
Family
ID=78672945
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110738499.6A Active CN113723102B (en) | 2021-06-30 | 2021-06-30 | Named entity recognition method, named entity recognition device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113723102B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108536679A (en) * | 2018-04-13 | 2018-09-14 | 腾讯科技(成都)有限公司 | Name entity recognition method, device, equipment and computer readable storage medium |
| WO2020164267A1 (en) * | 2019-02-13 | 2020-08-20 | 平安科技（深圳）有限公司 | Text classification model construction method and apparatus, and terminal and storage medium |
| CN111581361A (en) * | 2020-04-22 | 2020-08-25 | 腾讯科技（深圳）有限公司 | Intention identification method and device |
| CN111738003A (en) * | 2020-06-15 | 2020-10-02 | 中国科学院计算技术研究所 | Named entity recognition model training method, named entity recognition method, and medium |
| CN112183102A (en) * | 2020-10-15 | 2021-01-05 | 上海明略人工智能(集团)有限公司 | Named entity identification method based on attention mechanism and graph attention network |
| WO2021043085A1 (en) * | 2019-09-04 | 2021-03-11 | 平安科技（深圳）有限公司 | Method and apparatus for recognizing named entity, computer device, and storage medium |
| CN112667800A (en) * | 2020-12-21 | 2021-04-16 | 深圳壹账通智能科技有限公司 | Keyword generation method and device, electronic equipment and computer storage medium |
| CN113010690A (en) * | 2021-03-29 | 2021-06-22 | 华南理工大学 | Method for enhancing entity embedding based on text information |
-
2021
- 2021-06-30 CN CN202110738499.6A patent/CN113723102B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108536679A (en) * | 2018-04-13 | 2018-09-14 | 腾讯科技(成都)有限公司 | Name entity recognition method, device, equipment and computer readable storage medium |
| WO2020164267A1 (en) * | 2019-02-13 | 2020-08-20 | 平安科技（深圳）有限公司 | Text classification model construction method and apparatus, and terminal and storage medium |
| WO2021043085A1 (en) * | 2019-09-04 | 2021-03-11 | 平安科技（深圳）有限公司 | Method and apparatus for recognizing named entity, computer device, and storage medium |
| CN111581361A (en) * | 2020-04-22 | 2020-08-25 | 腾讯科技（深圳）有限公司 | Intention identification method and device |
| CN111738003A (en) * | 2020-06-15 | 2020-10-02 | 中国科学院计算技术研究所 | Named entity recognition model training method, named entity recognition method, and medium |
| CN112183102A (en) * | 2020-10-15 | 2021-01-05 | 上海明略人工智能(集团)有限公司 | Named entity identification method based on attention mechanism and graph attention network |
| CN112667800A (en) * | 2020-12-21 | 2021-04-16 | 深圳壹账通智能科技有限公司 | Keyword generation method and device, electronic equipment and computer storage medium |
| CN113010690A (en) * | 2021-03-29 | 2021-06-22 | 华南理工大学 | Method for enhancing entity embedding based on text information |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113723102A (en) | 2021-11-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114781402A (en) | Method and device for identifying inquiry intention, electronic equipment and readable storage medium | |
| CN113515938B (en) | Language model training method, device, equipment and computer readable storage medium | |
| CN112667878B (en) | Webpage text content extraction method and device, electronic equipment and storage medium | |
| CN113821622B (en) | Answer retrieval method and device based on artificial intelligence, electronic equipment and medium | |
| CN113360654B (en) | Text classification method, apparatus, electronic device and readable storage medium | |
| CN114021582B (en) | Spoken language understanding method, device, equipment and storage medium combined with voice information | |
| CN112257860A (en) | Model generation based on model compression | |
| CN115510188A (en) | Text keyword association method, device, equipment and storage medium | |
| CN116821373A (en) | Map-based prompt recommendation method, device, equipment and medium | |
| CN115238115A (en) | Image retrieval method, device and equipment based on Chinese data and storage medium | |
| CN114840684A (en) | Map construction method, device and equipment based on medical entity and storage medium | |
| KR102642488B1 (en) | Data providing device, method and computer program generating answer using artificial intelligence technology | |
| CN112668281A (en) | Automatic corpus expansion method, device, equipment and medium based on template | |
| CN113254814A (en) | Network course video labeling method and device, electronic equipment and medium | |
| CN110197521B (en) | Visual text embedding method based on semantic structure representation | |
| CN113723102B (en) | Named entity recognition method, named entity recognition device, electronic equipment and storage medium | |
| CN115169330B (en) | Chinese text error correction and verification method, device, equipment and storage medium | |
| CN116628162A (en) | Semantic question-answering method, device, equipment and storage medium | |
| US20240289552A1 (en) | Character-level attention neural networks | |
| CN116303945A (en) | Sample generation method of visual question-answering model and related equipment | |
| CN110851572A (en) | Session labeling method and device, storage medium and electronic equipment | |
| CN115346095A (en) | Visual question answering method, device, equipment and storage medium | |
| WO2022227196A1 (en) | Data analysis method and apparatus, computer device, and storage medium | |
| CN114742061A (en) | Text processing method and device, electronic equipment and storage medium | |
| CN114528459A (en) | Semantic-based webpage information extraction method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |