CN111680511A - Military field named entity identification method with cooperation of multiple neural networks - Google Patents

Military field named entity identification method with cooperation of multiple neural networks Download PDF

Info

Publication number
CN111680511A
CN111680511A CN202010315730.6A CN202010315730A CN111680511A CN 111680511 A CN111680511 A CN 111680511A CN 202010315730 A CN202010315730 A CN 202010315730A CN 111680511 A CN111680511 A CN 111680511A
Authority
CN
China
Prior art keywords
military
entity
sequence
layer
word
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.)
Pending
Application number
CN202010315730.6A
Other languages
Chinese (zh)
Inventor
尹学振
赵慧
陈沁蕙
李欣妍
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
East China Normal University
Original Assignee
East China Normal University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by East China Normal University filed Critical East China Normal University
Priority to CN202010315730.6A priority Critical patent/CN111680511A/en
Publication of CN111680511A publication Critical patent/CN111680511A/en
Pending legal-status Critical Current

Links

Images

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
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • G06F16/334—Query execution
    • G06F16/3344—Query execution using natural language analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35—Clustering; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/047—Probabilistic or stochastic networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Abstract

The invention provides a military field named entity identification method with multi-neural network cooperation, which comprises the following steps: step A: acquiring public microblog data to form an original data set; and B: combining with domain knowledge, proposing a military domain entity labeling strategy considering entity fuzzy boundaries, and formulating a military domain named entity classification standard; and C: b, performing text preprocessing on the original data set, and constructing a military corpus set MilitaryCorpus by combining the entity labeling strategy and the entity classification standard in the step B; step D: by utilizing a deep learning and statistical learning framework, a multi-neural-network collaborative military field named entity recognition model based on a BERT-BilSTM-CRF network structure is trained to perform a military field named entity recognition task aiming at Chinese social texts represented by microblogs.

Description

Military field named entity identification method with cooperation of multiple neural networks
Technical Field
The invention belongs to the technical field of military affairs, and relates to a named entity identification method based on multi-neural-network cooperation, in particular to a named entity identification method aiming at an entity in the field of military affairs.
Background
Named entity recognition is the fundamental work for conducting natural language processing research such as intelligent question answering and knowledge mapping, and is always concerned by researchers. Early named entity recognition research mostly adopts rule-based and dictionary-based methods, relies on a large number of manually set recognition rules, is difficult to fully cover the material, and the formulation of the rules often depends on a data set, and the rules need to be updated when the data set changes. The entity identification method based on statistical learning avoids formulation of a large number of rules, and converts the named entity identification problem into a serialization labeling problem, however, the named entity identification method based on statistical learning relies on predefined features, and feature engineering is not only high in cost but also related to a specific field, so that domain knowledge sacrifices the generalization capability and the migration capability of a model while improving the identification effectiveness of the model.
The improvement of computing power and the support of a distributed expression technology of words enable the named entity recognition task based on the deep neural network to be independent of feature engineering, and remarkable research progress is achieved. At present, research proves that the recognition accuracy of the word vector representation applied in the Chinese named entity recognition is superior to the mode of applying the word vector representation; the prior researchers use convolutional neural networks, BilSTM, CRF and the like to design model network structures, and obtain better identification effect in entity identification in the special fields of biological medicine and the like; aiming at the military field, some researchers carry out entity recognition work aiming at standard texts such as battle documents, imagination documents and the like, and obtain positive and objective research results. However, the entities in the standardized texts such as electronic medical records, military texts, battle papers and the like are relatively densely distributed and have certain rules, and the entity boundaries are relatively clear, while the entities in the social media data such as microblogs, Tweets and the like are sparsely distributed, the entity expression is not standard, and the entity boundaries are often not clear, so that how to perform named entity identification in the military field on the social media data such as microblogs and the like containing fuzzy boundary entities becomes a new research problem.
Disclosure of Invention
The invention aims to provide a named entity identification method in the military field, which comprises the following steps: an entity labeling mechanism aiming at entity fuzzy boundaries is provided to solve the problems that entity boundaries are difficult to define and entity simplified expressions are difficult to express in an entity identification task; a military field named entity recognition model (BERT-BilSTM-CRF) based on a transform based on multi-neural network cooperation and a two-way long-and-short-time memory neural network (BilSTM) and a Conditional Random Field (CRF) is utilized to solve the problems that a single CRF model needs to depend on a large amount of manual feature selection work and an LSTM model needs to depend on a huge corpus to construct word vectors, and the entity recognition effect is improved.
The invention provides a military field named entity identification method with multi-neural network cooperation, which comprises the following steps:
step A: acquiring public microblog text data to form an original data set;
and B: combining with domain knowledge, proposing a military domain entity labeling strategy considering entity fuzzy boundaries, and formulating a military domain named entity classification standard;
and C: b, performing text preprocessing on the original data set, and constructing a military corpus MilitaryCorpus by combining the entity labeling strategy and the entity classification standard in the step B;
step D: and training a multi-neural-network collaborative military field named entity recognition model based on a BERT-BilSTM-CRF network structure by utilizing a deep learning and statistical learning framework so as to carry out a military field named entity recognition task aiming at text data.
In the present invention, step B comprises:
step B1: in addition to general personnel names, times, place names, definitions are given for 5 categories of entities in the military domain, specific military rank and occupations, military agencies, military facilities, military events, weaponry: labeling buildings, sites and facilities representing for military purposes as military facility entities; labeling an institution, a military administration, a government agency, a combat unit, or an organization representing military association as a military agency entity; marking military exercises, armed conflicts, armed assaults, political events representing a relationship with the military field as military event entities; firearms, artillery, aircraft, ammunition, tanks, naval vessels, missiles, biochemical weapons, nuclear weapons are labeled as weaponry entities;
step B2: and (3) combining professional knowledge and literature data, proposing an entity labeling rule considering the fuzzy boundary:
rule 1: english letters, short transverse lines and numbers are connected with the weapon equipment, and the English letters, the short transverse lines, the numbers and the weapon equipment are marked as weapon equipment entities integrally;
rule 2: the military mechanism is connected with the weapon equipment, and if the weapon equipment is unique to the military mechanism, the weapon equipment is respectively marked as a military mechanism entity and a weapon equipment entity; if the weaponry is not unique to the military institution, the military institution and the weaponry are integrally labeled as weaponry entities;
rule 3: the military mechanism is connected with the military mechanism, and the whole body connected with the plurality of military mechanisms is marked as a military mechanism entity by taking the lowest mechanism level as the standard;
rule 4: connecting a military institution or a military place name with a military rank, and marking the connected whole as a military rank and a military entity;
rule 5: the military place name/military institution is connected with the military facility, and if the military facility is the military facility with a specific name, the military facility is respectively marked as a military place name/military institution entity and a military facility entity; if the military facility does not have a specific name, the connected whole is labeled as a military facility entity.
In the present invention, step C includes:
step C1: cleaning the original data set, deleting data without military information, and deleting special symbols in the data; the special symbols include: expressions and characters;
step C2: and C, combining the military field entity labeling strategy considering the entity fuzzy boundary in the step B and the military field named entity classification standard, and performing word-level labeling on the text processed in the step C1 to form a military field named entity corpus set MilitaryCorpus.
In the present invention, step D comprises:
step D1: the military corpus is divided into sentence levels according to each character x in the text sequenceijkGenerating a feature vector ckThe feature vector c is processed by a transform-based bidirectional encoderkConversion into a word vector E with word and position featuresk；
Step D2: inputting the word vector sequence into a bidirectional long-short time memory neural network to extract context characteristics and generate a characteristic matrix Pk；
Step D3: CRF layer based on feature vector ckCapturing the dependency relationship between adjacent labels, and determining the label sequence optimized by the whole sentence according to the dependency relationship between the adjacent labels.
Wherein, the word vector expression layer based on BERT in step D1 implements:
for MilitaryCorpus corpora, corpus s is concentratedij＝(xij1，xij2，...，xijn) Calculates 3 features per word: word feature, sentence feature, position feature definition sij＝(xij1，xij2，...，xijn) is characterized by
Figure BDA0002459490570000031
Is a sentence feature, a location feature is
Figure BDA0002459490570000032
When the character features are generated, aiming at xijk, a BERT vocabulary is adopted to determine the corresponding character vector
Figure BDA0002459490570000033
Each time the recognition unit is a sentence, the sentence characteristic is set to 0, namely for the recognition unit
Figure BDA0002459490570000039
Is provided with
Figure BDA0002459490570000035
Figure BDA0002459490570000036
Wherein the content of the first and second substances,
Figure BDA0002459490570000037
the position characteristic of the kth word is represented, namely k; the BERT-based word vector representation layer inputs numerical values and position characteristics of word characteristics, sentence characteristics and position characteristics
Figure BDA0002459490570000038
Wherein, Ck∈C，C＝(C1，C2，C3，...，Cn)；
Said C ═ C1，C2，C3，...，Cn) And (E) outputting a final characteristic vector E through multi-layer transform calculation1，E2，E3，...，En) (ii) a The output matrix of each Transformer node is used as the input of all the Transformer nodes in the previous layer, and then the calculation is carried out by using the calculation mechanism of BERT to obtain the word-level eigenvector sequence E ═ E1，E2，E3，...，En) As input to the BiLSTM neural network layer.
And D2, realizing based on a bidirectional long-time memory neural network layer:
BERT-based word vector representation layer E ═ (E)1，E2，E3，...，En) As the input of the layer, performing characteristic calculation in the hidden node corresponding to the time point; the output sequence of the forward LSTM hidden layer is F ═ F (F)1，F2，F3，...，Fn)，F1Is input as E1From F2Start of
Figure BDA0002459490570000041
Input is as
Figure BDA0002459490570000042
The output sequence of the backward LSTM hidden layer is B ═ B (B)1，B2，B3，...，Bn)，B1Is input as E1From B2Start of
Figure BDA0002459490570000043
Input is as
Figure BDA0002459490570000044
For EkCalculating an output vector PkI.e. by
Figure BDA0002459490570000045
Finally, the output of the BilSTM neural network is given E ═ E (E)1，E2，E3，...，En) Generating a feature matrix P ∈ R
Figure BDA0002459490570000046
pyzRepresenting an input sentence sijChinese character xyIs the z-tag probability; the feature matrix P is used as input to the CRF layer to generate sij＝(xij1，xij2，...，xijn) The tag sequence of (1).
Wherein, the CRF layer in step D3 implements:
for the output matrix P of the BilSTM neural network layer, the inputs (x) to the model are definedij1，xij2，...，xijn) The sequence of the mark is (y ═ y1，y2，y3，...，yn) While defining the transition matrix as
Figure BDA0002459490570000047
Wherein m is the number of entity types, aijRepresenting the probability of label i transitioning to label j, the tag sequence y ═ y (y) is generated1，y2，y3，...，yn) The score function is:
Figure BDA0002459490570000048
wherein y is0Denotes SijStart tag of yn+1Denotes SijThe end tag of (a), which is used only as a marker and is not included in the final predicted tag sequence;
Figure BDA0002459490570000049
indicates that the label is represented by ykTransfer to yk+1The probability of (a) of (b) being,
Figure BDA00024594905700000410
obtained by an output matrix of a context feature extraction part based on the BilSTM, and represents SijIn xijkThe label is ykThe probability of (d); calculating y ═ y (y) by the transition matrix and the output matrix of the context feature extraction part based on BilSTM1，y2，y3，...，yn) The fraction of the sequence is input to the softmax function; calculating S using equation (2)ijEach possible predicted sequence probability of:
Figure BDA0002459490570000054
wherein Y isXIs shown for SijAll of the possible predicted tag sequences are,
Figure BDA0002459490570000051
representing the actual marker sequence;
in the training process, in order to obtain the optimal predicted label sequence, p (ys) is required to be enabledij) Maximization, for ease of calculation, p (y | s) is calculated based on equation (3)ij) And (3) solving the log likelihood:
Figure BDA0002459490570000052
by log (p (y | s)ij) Maximization, and obtaining a globally optimal label sequence based on a CRF coding part; in the decoding stage, a group of sequences with the highest overall probability are obtained as the optimal label sequences based on the formula (4), and the optimal label sequences are used as the output of the CRF-based coding global optimal label:
Figure BDA0002459490570000053
the technical scheme adopted by the invention has the following technical characteristics:
1) the invention provides an entity labeling mechanism aiming at entity fuzzy boundaries by combining the opinions of field experts, and constructs a military field corpus MilitaryCorpus based on open data.
2) A military field named entity recognition model (BERT-BilSTM-CRF) based on a transform-based Bidirectional Encoder (BERT) and a bidirectional long-and-short time memory neural network (BilSTM) and a Conditional Random Field (CRF) in cooperation with a multi-neural network is provided as a core military field entity recognition method.
3) Compared with the dominant entity recognition models such as a named entity recognition model (CRF) based on CRF, a named entity recognition model (BilSTM-CRF) based on bidirectional LSTM (BilSTM) and CRF, a named entity recognition model (CNN-BilSTM-CRF) based on Convolutional Neural Network (CNN), BilSTM and CRF and the like, the military field entity recognition method based on multi-neural network cooperation provided by the invention combines word characteristics, sentence characteristics and position characteristics to generate a word vector, uses a Transformer training word vector, fully considers the influence of context information on an entity, and overcomes the defect that the entity recognition is carried out by only considering the characteristics of a word and neglecting the context combined context in the feature vector combined with the word level. The method has the advantages of higher effectiveness and better recognition effect.
Drawings
FIG. 1 is a block diagram of a multi-neural network collaborative military domain entity recognition model according to the present invention
FIG. 2 is a schematic diagram of the input of a word vector expression layer based on BERT of the named entity recognition model proposed by the present invention;
fig. 3 is an overall schematic diagram of a BERT-representing layer in the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention are clearly and completely described below with reference to the specific embodiments. The embodiments described below are only a part of the embodiments of the present invention, and not all of them. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
The invention provides a technical method of a military field named entity recognition model with multi-neural network cooperation
The scheme is as follows:
1) an entity labeling strategy considering entity fuzzy boundaries is proposed, and a military corpus set MilitaryCorpus based on microblog data is constructed by combining domain expert knowledge, and the method specifically comprises the following steps:
a) selecting 21711 microblogs of 'New wave military', 'gathering number', 'micro military situation', 3 microblog accounts from 12 months in 2013 to 12 months in 2018 as an original data set;
b) an entity labeling rule considering the fuzzy boundary is proposed by combining the professional knowledge of a domain expert and the existing literature data, and the division category of the named entity facing the military domain is determined;
c) cleaning the original data, and deleting the microblog which only contains the facial expression, the advertisement information, the recruitment information and the like and does not contain military information;
d) and marking the linguistic data in the unmarked original corpus according to the word level to form a military field named entity linguistic data set MilitaryCorpus.
2) A military field named entity recognition model with multi-neural network cooperation is constructed, and as shown in figure 1, the specific steps are as follows:
a) dividing the microblog into sentence levels according to each character x in the text sequenceijkGenerating a feature vector ckA Transformer-based Bidirectional Encoder (BERT) will ckConversion into a word vector E with word and position featuresk；
b) Inputting the word vector sequence into a bidirectional long-short time memory network (BilSTM), extracting context characteristics and generating a characteristic matrix Pk；
c) And finally, the CRF layer captures the dependency relationship between the adjacent labels according to the characteristic vector and determines the label sequence optimized by the whole sentence according to the dependency relationship between the adjacent labels.
Further, the specific content of the entity labeling rule considering the fuzzy boundary in the step (1b) is as follows:
in addition to general personnel names, times, place names, definitions are given for 5 categories of entities in the military domain, specific military rank and occupations, military agencies, military facilities, military events, weaponry: labeling buildings, sites and facilities representing for military purposes as military facility entities; labeling an institution, a military administration, a government agency, a combat unit, or an organization representing military association as a military agency entity; marking military exercises, armed conflicts, armed assaults, political events representing a relationship with the military field as military event entities; firearms, artillery, aircraft, ammunition, tanks, naval vessels, missiles, biochemical weapons, nuclear weapons are labeled weaponry entities. Meanwhile, referring to the military language and the suggestion of domain experts, an entity labeling rule considering the fuzzy boundary is provided.
Rule 1: english letters, (dash), numerals are associated with the weaponry and english letters, (dash), numerals are labeled as weaponry entities in their entirety. Such as: { ZTZ-99 type tank }.
Rule 2: the military mechanism is connected with the weapon equipment, and if the weapon equipment is unique to the military mechanism, the weapon equipment is respectively marked as a military mechanism entity and a weapon equipment entity; if the weaponry is not unique to the military entity, the military entity and the ensemble of weaponry are labeled weaponry entities. Such as: { the Russian, graph-160 bomber }, and { the Russian bomber }.
Rule 3: the military mechanism is connected with the military mechanism, and the whole body connected with the plurality of military mechanisms is marked as a military mechanism entity by taking the lowest mechanism level as the standard. Such as: { certain engineer infantry travel }.
Rule 4: military agencies or names of military sites are connected to the military rank, and the connected whole is labeled as the military rank and military-occupational entity. Such as: { japanese defending against growth }.
Rule 5: the military place name (or military organization) is connected with the military facility, and if the military facility is the military facility with a specific name, the military place name (or military organization) entity and the military facility entity are respectively marked; a connected whole is labeled as a military facility entity if the military facility does not have a specific name. Such as: { australia, willingston air force base }.
By the entity labeling mechanism, the problems of fuzzy entity boundary and difficult entity boundary determination in the process of labeling the named entities in the military field are solved.
Further, the specific content of the classification categories facing the military domain named entities in the step (1d) is as follows:
aiming at the characteristics of more professional terms and less ambiguity of the named entities in the military field, the invention adopts a simple and efficient BIO labeling mechanism and is commonly labeled by field experts. BIO notation is a word-level position notation for each entity in the data set, B is used for representing the beginning of the named entity, I is used for representing the inside of the named entity, and O is used for representing a word not belonging to the named entity. The specific labeling is shown in table 1.
TABLE 1 military Domain named entity tagging Categories
Entity classes Entity initiation Inside the entity
Name of person (P) B-P I-P
Military place name (L) B-L I-L
Time (T) B-T I-T
Military rank or military position (R) B-R I-R
Military mechanism (G) B-G I-G
Military equipment (F) B-F I-F
Military affairs (E) B-E I-E
Military weapon (W) B-W I-W
Further, the implementation details of the BERT-based word vector expression layer in step (2a) are as follows:
according to the invention, a word vector expression layer based on the BERT is constructed according to the fine tuning mechanism provided by the BERT and the particularity of the naming recognition problem in the field of Chinese military, and the generation work of the word vector is completed.
To sij＝(xij1，xij2，...，xijn) Calculates 3 features per word: word feature, sentence feature, position feature definition sij＝(xij1，xij2，...，xijn) Is characterized by
Figure BDA0002459490570000081
Figure BDA0002459490570000082
Is a sentence feature, a location feature is
Figure BDA0002459490570000083
. In word feature generation, for xijkDetermining the corresponding word vector by adopting the BERT vocabulary provided by Google
Figure BDA0002459490570000084
The model is input based on sentences, each time the recognition unit is a sentence, the characteristics of the sentence are invalid for the entity recognition, so the invention sets the sentence characteristics to 0, namely for the sentence
Figure BDA0002459490570000089
Is provided with
Figure BDA0002459490570000086
Figure BDA0002459490570000087
The position characteristic of the kth word is represented as k. The BERT-based word vector representation layer inputs numerical values and position characteristics of word characteristics, sentence characteristics and position characteristics
Figure BDA0002459490570000088
Wherein C isk∈C，C＝(C1，C2，C3，...，Cn) As shown in fig. 2.
Obtained C ═ C1，C2，C3，...，Cn) And (E) outputting a final characteristic vector E through multi-layer transform calculation1，E2，E3，...，En). The output matrix of each Transformer node is used as the input of all the Transformer nodes in the previous layer, and then the calculation is carried out by using the calculation mechanism of BERT to obtain the word-level eigenvector sequence E ═ E1，E2，E3，...，En) As a BilsTM neural netThe input of the envelope layer is not shown in FIG. 3.
Further, the specific content of the BilSTM neural network layer in the step (2b) is as follows:
the long-distance dependence problem exists in named entities in the military field, and the method is solved by using a bidirectional long-time neural network (BilSTM). BERT-based word vector representation layer E ═ (E)1，E2，E3，...，En) And as the input of the layer, performing characteristic calculation in the hidden node corresponding to the time point. The output sequence of the forward LSTM hidden layer is F ═ F (F)1，F2，F3，...，Fn)，F1Is input as E1From F2Start of
Figure BDA0002459490570000091
Input is as
Figure BDA0002459490570000092
The output sequence of the backward LSTM hidden layer is B ═ B (B)1，B2，B3，...，Bn)，B1Is input as E1From B2Start of
Figure BDA0002459490570000093
Input is as
Figure BDA0002459490570000094
For EkCalculating an output vector PkI.e. by
Figure BDA0002459490570000095
Finally, the output of the BilSTM neural network is given E ═ E (E)1，E2，E3，...，En) Generating a feature matrix P ∈ R
Figure BDA0002459490570000096
pyzRepresenting an input sentence sijChinese character xyIs the z-tag probability. The feature matrix P is used as input to the CRF layer to generate sij＝(xij1，xij2，...，xijn) The tag sequence of (1).
Further, the specific content of the CRF layer in step (2c) is:
the CRF layer obtains a global optimal marking sequence through the relation of adjacent labels, and adds constraint to the last predicted label:
1) the first word in the sentence starts with the tag "B-" or "O-" and tags starting with "O-" cannot be connected in sequence with the tag "I-";
2) in the label B-X1I-X2I-X3, X1, X2 and X3 belong to the same category; based on these constraints, the probability of illegal sequences occurring in the tag sequence prediction is reduced;
for the output matrix P of the BilSTM neural network layer, the inputs (x) to the model are definedij1，xij2，...，xijn) The sequence of the mark is (y ═ y1，y2，y3，...，yn) While defining the transition matrix as
Figure BDA0002459490570000097
Wherein m is the number of entity types, aijRepresenting the probability of label i transitioning to label j, the tag sequence y ═ y (y) is generated1，y2，y3，...，yn) The score function is:
Figure BDA0002459490570000098
wherein y is0Denotes SijStart tag of yn+1Denotes SijThe end tag of (2) is used only as a marker and is not included in the final predicted tag sequence.
Figure BDA0002459490570000105
Indicates that the label is represented by ykTransfer to yk+1The probability of (a) of (b) being,
Figure BDA0002459490570000106
obtained by an output matrix of a context feature extraction part based on the BilSTM, and represents SijIn xijkThe label is ykThe probability of (c). Calculating y ═ y (y) by the transition matrix and the output matrix of the context feature extraction part based on BilSTM1，y2，y3，...，yn) The score of the sequence and input to the softmax function. Calculating S using equation (2)ijIs determined for each possible predicted sequence probability.
Figure BDA0002459490570000101
Wherein Y isXIs shown for SijAll of the possible predicted tag sequences are,
Figure BDA0002459490570000102
representing the actual marker sequence.
In the training process, in order to obtain the optimal predicted label sequence, p (ys) is required to be enabledij) Maximization, for ease of calculation, p (y | s) is calculated based on equation (3)ij) And (6) solving the log likelihood.
Figure BDA0002459490570000103
By log (p (y | s)ij) ) to maximize, a globally optimal tag sequence is obtained based on the encoded portion of the CRF. In the decoding stage, a group of sequences with the highest overall probability are obtained as the optimal label sequence based on the formula (4) and are used as the output of the CRF-based encoding global optimal label.
Figure BDA0002459490570000104
Examples
The invention provides a military field named entity identification method with multi-neural network cooperation, which comprises the following specific implementation examples:
step 1: in this embodiment, 21711 microblogs from "new wave military", "staging number", and "micro military situation" 3 microblog accounts from 12 months in 2013 to 12 months in 2018 are used as the original data set.
Step 2: in this embodiment, the acquired microblog data needs to be cleaned, the microblog containing only the facial expression, the advertisement information, the recruitment information and the like and not containing military information is deleted, and then punctuation marks are used. ","? ","! "," … … "is used as mark to divide the washed data in sentence level, and the divided sentences are stored in excel for the following part of speech tagging.
And step 3: the embodiment applies the fuzzy boundary entity labeling rule provided in the invention, determines the classification category of the named entity facing the military field by combining the professional knowledge of the field expert and the existing literature data, and classifies the named entity of the military field into 8 categories, namely, the name of a person, the name of a military place, the time, the rank of a military or military post, a military institution, a military facility, a military event, weaponry and other categories. And labeling the linguistic data in the unlabeled original corpus according to the word level, and finally constructing a linguistic data set MilitaryCorpus containing 15317 microblogs, 20388 sentences and personnel names, military place names, time, military rank or military occupations, military institutions, military facilities, military events and 8 categories of military weaponry.
And 4, step 4: according to the fine tuning mechanism provided by the BERT and the particularity of the naming recognition problem of the Chinese military field, a word vector expression layer based on the BERT is constructed, and the generation work of the word vector is completed.
To sij＝(xij1，xij2，...，xijn) Calculates 3 features per word: word feature, sentence feature, position feature definition sij＝(xij1，xij2，...，xijn) Is characterized by
Figure BDA0002459490570000111
Figure BDA0002459490570000112
Is a sentence feature, a location feature is
Figure BDA0002459490570000113
In word feature generation, for xijkUsing Google determine the word vector corresponding to the BERT vocabulary
Figure BDA0002459490570000114
The model is input based on sentences, each time the recognition unit is a sentence, the characteristics of the sentence are invalid for the entity recognition, so the invention sets the sentence characteristics to 0, namely for the sentence
Figure BDA0002459490570000115
Is provided with
Figure BDA0002459490570000116
Figure BDA0002459490570000117
The position characteristic of the kth word is represented as k. The BERT-based word vector representation layer inputs numerical values and position characteristics of word characteristics, sentence characteristics and position characteristics
Figure BDA0002459490570000118
Wherein C isk∈C，C＝(C1，C2，C3，...，Cn) As shown in fig. 2.
Obtained C ═ C1，C2，C3，...，Cn) And (E) outputting a final characteristic vector E through multi-layer transform calculation1，E2，E3，...，En). The output matrix of each Transformer node is used as the input of all the Transformer nodes in the previous layer, and then the calculation is carried out by using the calculation mechanism of BERT to obtain the word-level eigenvector sequence E ═ E1，E2，E3，...，En) As input to the BiLSTM neural network layer, as shown in fig. 3.
And 5: BERT-based word vector representation layer E ═ (E)1，E2，E3，...，En) And as the input of the layer, performing characteristic calculation in the hidden node corresponding to the time point. The output sequence of the forward LSTM hidden layer is F ═ F (F)1，F2，F3，...，Fn)，F1Is input as E1From F2Start of
Figure BDA0002459490570000119
Input is as
Figure BDA00024594905700001110
The output sequence of the backward LSTM hidden layer is B ═ B (B)1，B2，B3，...，Bn)，B1Is input as E1From B2Start of
Figure BDA0002459490570000121
Input is as
Figure BDA0002459490570000122
For EkCalculating an output vector PkI.e. by
Figure BDA0002459490570000123
Finally, the output of the BilSTM neural network is given E ═ E (E)1，E2，E3，...，En) Generating a feature matrix P ∈ R
Figure BDA0002459490570000124
pyzRepresenting an input sentence sijChinese character xyIs the z-tag probability. The feature matrix P is used as input to the CRF layer to generate sij＝(xij1，xij2，...，xijn) The tag sequence of (1). Step 6: for the output matrix P of the BilSTM neural network layer, the inputs (x) to the model are definedij1，xij2，...，xijn) The sequence of the mark is (y ═ y1，y2，y3，...，yn) While defining the transition matrix as
Figure BDA0002459490570000125
Wherein m is the number of entity types, aijRepresenting the probability of label i transitioning to label j, the tag sequence y ═ y (y) is generated1，y2，y3，...，yn) The score function is:
Figure BDA0002459490570000126
wherein y is0Denotes SijStart tag of yn+1Denotes SijThe end tag of (2) is used only as a marker and is not included in the final predicted tag sequence.
Figure BDA0002459490570000129
Indicates that the label is represented by ykTransfer to yk+1The probability of (a) of (b) being,
Figure BDA00024594905700001210
obtained by an output matrix of a context feature extraction part based on the BilSTM, and represents SijIn xijkThe label is ykThe probability of (c). Calculating y ═ y (y) by the transition matrix and the output matrix of the context feature extraction part based on BilSTM1，y2，y3，...，yn) The score of the sequence and input to the softmax function. Calculating s using equation (2)ijIs determined for each possible predicted sequence probability.
Figure BDA0002459490570000127
Wherein Y isXIs shown for SijAll of the possible predicted tag sequences are,
Figure BDA0002459490570000128
representing the actual marker sequence.
In the training process, in order to obtain the optimal predicted label sequence, p (ys) is required to be enabledij) Maximization, for ease of calculation, p (y | s) is calculated based on equation (3)ij) And (6) solving the log likelihood.
Figure BDA0002459490570000131
By log (p (y | s)ij) Maximizing, CRF-based encoding sectionAnd (4) obtaining a globally optimal label sequence. In the decoding stage, a group of sequences with the highest overall probability are obtained as the optimal label sequence based on the formula (4) and are used as the output of the CRF-based encoding global optimal label.
Figure BDA0002459490570000132
The invention is not the best known technology.
The above embodiments are merely illustrative of the technical ideas and features of the present invention, and the purpose thereof is to enable those skilled in the art to understand the contents of the present invention and implement the present invention, and not to limit the protection scope of the present invention. All equivalent changes and modifications made according to the spirit of the present invention should be covered within the protection scope of the present invention.

Claims (8)

1. A military field named entity identification method with cooperation of multiple neural networks is characterized by comprising the following steps:
step A: acquiring public text data to form an original data set;
and B: combining with domain knowledge, proposing a military domain entity labeling strategy considering entity fuzzy boundaries, and formulating a military domain named entity classification standard;
and C: b, performing text preprocessing on the original data set, and constructing a military corpus MilitaryCorpus by combining the entity labeling strategy and the entity classification standard in the step B;
step D: and training a multi-neural-network collaborative military field named entity recognition model based on a BERT-BilSTM-CRF network structure by utilizing a deep learning and statistical learning framework so as to carry out a military field named entity recognition task aiming at text data.
2. The method of multi-neural-network-cooperative military-domain named entity recognition of claim 1, wherein the textual data is derived from a microblog.
3. The method of multi-neural-network-cooperative military-domain named entity recognition of claim 1, wherein step B comprises:
step B1: in addition to general personnel names, times, place names, definitions are given for 5 categories of entities in the military domain, specific military rank and occupations, military agencies, military facilities, military events, weaponry: labeling buildings, sites and facilities representing for military purposes as military facility entities; labeling an institution, a military administration, a government agency, a combat unit, or an organization representing military association as a military agency entity; marking military exercises, armed conflicts, armed assaults, political events representing a relationship with the military field as military event entities; firearms, artillery, aircraft, ammunition, tanks, naval vessels, missiles, biochemical weapons, nuclear weapons are labeled as weaponry entities;
step B2: and (3) combining professional knowledge and literature data, proposing an entity labeling rule considering the fuzzy boundary:
rule 1: english letters, short transverse lines and numbers are connected with the weapon equipment, and the English letters, the short transverse lines, the numbers and the weapon equipment are marked as weapon equipment entities integrally;
rule 2: the military mechanism is connected with the weapon equipment, and if the weapon equipment is unique to the military mechanism, the weapon equipment is respectively marked as a military mechanism entity and a weapon equipment entity; if the weaponry is not unique to the military institution, the military institution and the weaponry are integrally labeled as weaponry entities;
rule 3: the military mechanism is connected with the military mechanism, and the whole body connected with the plurality of military mechanisms is marked as a military mechanism entity by taking the lowest mechanism level as the standard;
rule 4: connecting a military institution or a military place name with a military rank, and marking the connected whole as a military rank and a military entity;
rule 5: the military place name/military institution is connected with the military facility, and if the military facility is the military facility with a specific name, the military facility is respectively marked as a military place name/military institution entity and a military facility entity; if the military facility does not have a specific name, the connected whole is labeled as a military facility entity.
4. The method of multi-neural-network-cooperative military-domain named entity recognition of claim 1, wherein step C comprises:
step C1: cleaning the original data set, deleting data without military information, and deleting special symbols in the data; the special symbols include: expressions and characters;
step C2: and C, combining the military field entity labeling strategy considering the entity fuzzy boundary in the step B and the military field named entity classification standard, and performing word-level labeling on the text processed in the step C1 to form a military field named entity corpus set MilitaryCorpus.
5. The method of multi-neural-network-cooperative military-domain named entity recognition of claim 1, wherein step D comprises:
step D1: the military corpus is divided into sentence levels according to each character x in the text sequenceijkGenerating a feature vector ckThe feature vector c is processed by a transform-based bidirectional encoderkConversion into a word vector E with word and position featuresk；
Step D2: inputting the word vector sequence into a bidirectional long-short time memory neural network to extract context characteristics and generate a characteristic matrix Pk；
Step D3: CRF layer based on feature vector ckCapturing the dependency relationship between adjacent labels, and determining the label sequence optimized by the whole sentence according to the dependency relationship between the adjacent labels.
6. The method for military domain named entity recognition with multi-neural network cooperation of claim 5, wherein the BERT-based word vector expression layer in step D1 implements:
for MilitaryCorpus corpora, corpus s is concentratedij＝(xij1，xij2，...，xijn) Calculates 3 features per word: word feature, sentence feature, position feature definition sij＝(xij1，xij2，...，xijn) Is characterized by
Figure FDA0002459490560000021
Is a sentence feature, a location feature is
Figure FDA0002459490560000022
In word feature generation, for xijkDetermining the corresponding word vector by using BERT vocabulary
Figure FDA0002459490560000023
Each time the recognition unit is a sentence, the sentence characteristic is set to 0, namely for the recognition unit
Figure FDA0002459490560000031
k2Is provided with
Figure FDA0002459490560000032
Figure FDA0002459490560000033
Wherein the content of the first and second substances,
Figure FDA0002459490560000034
the position characteristic of the kth word is represented, namely k; the BERT-based word vector representation layer inputs numerical values and position characteristics of word characteristics, sentence characteristics and position characteristics
Figure FDA0002459490560000035
Wherein, Ck∈C，C＝(C1，C2，C3，...，Cn)；
Said C ═ C1，C2，C3，...，Cn) And (E) outputting a final characteristic vector E through multi-layer transform calculation1，E2，E3，...，En) (ii) a The output matrix of each transform node is used as the input of all transform nodes in the previous layer, howeverAnd then using a computing mechanism of BERT to compute to obtain a character-level feature vector sequence E ═ (E)1，E2，E3，...，En) As input to the BiLSTM neural network layer.
7. The method for identifying military domain named entities with multi-neural network cooperation according to claim 5, wherein the step D2 is implemented based on a bidirectional long-and-short memory neural network layer:
BERT-based word vector representation layer E ═ (E)1，E2，E3，...，En) As the input of the layer, performing characteristic calculation in the hidden node corresponding to the time point; the output sequence of the forward LSTM hidden layer is F ═ F (F)1，F2，F3，...，Fn)，F1Is input as E1From F2Start of
Figure FDA0002459490560000036
Input is as
Figure FDA0002459490560000037
The output sequence of the backward LSTM hidden layer is S ═ B1，B2，B3，...，Bn)，B1Is input as E1From B2Start of
Figure FDA0002459490560000038
Input is as
Figure FDA0002459490560000039
For EkCalculating an output vector PkI.e. by
Figure FDA00024594905600000310
Finally, the output of the BilSTM neural network is given E ═ E (E)1，E2，E3，...，En) Generating a feature matrix P ∈ R
Figure FDA00024594905600000311
pyzRepresenting an input sentence sijChinese character xyIs the z-tag probability; the feature matrix P is used as input to the CRF layer to generate sij＝(xij1，xij2，...，xijn) The tag sequence of (1).
8. The method for identifying military domain named entities with multi-neural network cooperation according to claim 5, wherein in the step D3, the CRF layer realizes that:
for the output matrix P of the BilSTM neural network layer, the inputs (x) to the model are definedij1，xij2，...，xijn) The sequence of the mark is (y ═ y1，y2，y3，...，yn) While defining the transition matrix as
Figure FDA00024594905600000312
Wherein m is the number of entity types, aijRepresenting the probability of label i transitioning to label j, the tag sequence y ═ y (y) is generated1，y2，y3，...，yn) The score function is:
Figure FDA0002459490560000041
wherein, y0Denotes SijStart tag of yn+1Denotes SijThe end tag of (a), which is used only as a marker and is not included in the final predicted tag sequence;
Figure FDA0002459490560000046
yk+1indicates that the label is represented by ykTransfer to yk+1The probability of (a) of (b) being,
Figure FDA0002459490560000047
obtained by an output matrix of a context feature extraction part based on the BilSTM, and represents SijIn xijkThe label is ykThe probability of (d); by shifting the sum of matricesCalculating y ═ y based on an output matrix of a context feature extraction part of the BilSTM1，y2，y3，...，yn) The fraction of the sequence is input to the softmax function; calculating S using equation (2)ijEach possible predicted sequence probability of:
Figure FDA0002459490560000042
wherein, YXIs shown for SijAll of the possible predicted tag sequences are,
Figure FDA0002459490560000043
representing the actual marker sequence;
in the training process, in order to obtain the optimal predicted label sequence, p (ys) is required to be enabledij) Maximization, for ease of calculation, p (y | s) is calculated based on equation (3)ij) And (3) solving the log likelihood:
Figure FDA0002459490560000044
by log (p (y | s)ij) Maximization, and obtaining a globally optimal label sequence based on a CRF coding part; in the decoding stage, a group of sequences with the highest overall probability are obtained as the optimal label sequences based on the formula (4), and the optimal label sequences are used as the output of the CRF-based coding global optimal label:
Figure FDA0002459490560000045
CN202010315730.6A 2020-04-21 2020-04-21 Military field named entity identification method with cooperation of multiple neural networks Pending CN111680511A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010315730.6A CN111680511A (en) 2020-04-21 2020-04-21 Military field named entity identification method with cooperation of multiple neural networks

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010315730.6A CN111680511A (en) 2020-04-21 2020-04-21 Military field named entity identification method with cooperation of multiple neural networks

Publications (1)

Publication Number Publication Date
CN111680511A true CN111680511A (en) 2020-09-18

Family

ID=72451730

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010315730.6A Pending CN111680511A (en) 2020-04-21 2020-04-21 Military field named entity identification method with cooperation of multiple neural networks

Country Status (1)

Country Link
CN (1) CN111680511A (en)

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112115238A (en) * 2020-10-29 2020-12-22 电子科技大学 Question-answering method and system based on BERT and knowledge base
CN112183058A (en) * 2020-09-22 2021-01-05 甘肃农业大学 Poetry generation method and device based on BERT sentence vector input
CN112257442A (en) * 2020-09-27 2021-01-22 重庆生产力促进中心 Policy document information extraction method based on corpus expansion neural network
CN112422712A (en) * 2020-11-10 2021-02-26 山东伏羲智库互联网研究院 Distributed domain name storage method and system
CN112668335A (en) * 2020-12-21 2021-04-16 广州市申迪计算机系统有限公司 Method for identifying and extracting business license structured information by using named entity
CN112765957A (en) * 2021-02-27 2021-05-07 中电万维信息技术有限责任公司 Punctuation-free text clause dividing method
CN113220871A (en) * 2021-05-31 2021-08-06 北京语言大学 Literature character relation identification method based on deep learning
CN113806481A (en) * 2021-09-17 2021-12-17 中国人民解放军国防科技大学 Operation event extraction method oriented to encyclopedic data
CN113849597A (en) * 2021-08-31 2021-12-28 艾迪恩(山东)科技有限公司 Illegal advertising word detection method based on named entity recognition
CN113869054A (en) * 2021-10-13 2021-12-31 天津大学 Deep learning-based electric power field project feature identification method
CN113901826A (en) * 2021-12-08 2022-01-07 中国电子科技集团公司第二十八研究所 Military news entity identification method based on serial mixed model
CN114186690A (en) * 2022-02-16 2022-03-15 中国空气动力研究与发展中心计算空气动力研究所 Aircraft knowledge graph construction method, device, equipment and storage medium
WO2023092960A1 (en) * 2022-04-24 2023-06-01 之江实验室 Labeling method and apparatus for named entity recognition in legal document
CN116662582A (en) * 2023-08-01 2023-08-29 成都信通信息技术有限公司 Specific domain business knowledge retrieval method and retrieval device based on natural language

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110032737A (en) * 2019-04-10 2019-07-19 贵州大学 A kind of boundary combinations name entity recognition method neural network based
CN110879831A (en) * 2019-10-12 2020-03-13 杭州师范大学 Chinese medicine sentence word segmentation method based on entity recognition technology
US20220188520A1 (en) * 2019-03-26 2022-06-16 Benevolentai Technology Limited Name entity recognition with deep learning

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220188520A1 (en) * 2019-03-26 2022-06-16 Benevolentai Technology Limited Name entity recognition with deep learning
CN110032737A (en) * 2019-04-10 2019-07-19 贵州大学 A kind of boundary combinations name entity recognition method neural network based
CN110879831A (en) * 2019-10-12 2020-03-13 杭州师范大学 Chinese medicine sentence word segmentation method based on entity recognition technology

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
尹学振: "多神经网络协作的军事领域命名实体识别", 《清华大学学报(自然科学版)》 *

Cited By (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112183058A (en) * 2020-09-22 2021-01-05 甘肃农业大学 Poetry generation method and device based on BERT sentence vector input
CN112257442A (en) * 2020-09-27 2021-01-22 重庆生产力促进中心 Policy document information extraction method based on corpus expansion neural network
CN112257442B (en) * 2020-09-27 2023-01-24 重庆生产力促进中心 Policy document information extraction method based on corpus expansion neural network
CN112115238B (en) * 2020-10-29 2022-11-15 电子科技大学 Question-answering method and system based on BERT and knowledge base
CN112115238A (en) * 2020-10-29 2020-12-22 电子科技大学 Question-answering method and system based on BERT and knowledge base
CN112422712A (en) * 2020-11-10 2021-02-26 山东伏羲智库互联网研究院 Distributed domain name storage method and system
CN112422712B (en) * 2020-11-10 2023-05-23 山东伏羲智库互联网研究院 Distributed domain name storage method and system
CN112668335A (en) * 2020-12-21 2021-04-16 广州市申迪计算机系统有限公司 Method for identifying and extracting business license structured information by using named entity
CN112765957A (en) * 2021-02-27 2021-05-07 中电万维信息技术有限责任公司 Punctuation-free text clause dividing method
CN113220871A (en) * 2021-05-31 2021-08-06 北京语言大学 Literature character relation identification method based on deep learning
CN113220871B (en) * 2021-05-31 2023-10-20 山东外国语职业技术大学 Literature character relation recognition method based on deep learning
CN113849597A (en) * 2021-08-31 2021-12-28 艾迪恩(山东)科技有限公司 Illegal advertising word detection method based on named entity recognition
CN113849597B (en) * 2021-08-31 2024-04-30 艾迪恩(山东)科技有限公司 Illegal advertisement word detection method based on named entity recognition
CN113806481A (en) * 2021-09-17 2021-12-17 中国人民解放军国防科技大学 Operation event extraction method oriented to encyclopedic data
CN113869054A (en) * 2021-10-13 2021-12-31 天津大学 Deep learning-based electric power field project feature identification method
CN113901826A (en) * 2021-12-08 2022-01-07 中国电子科技集团公司第二十八研究所 Military news entity identification method based on serial mixed model
CN114186690A (en) * 2022-02-16 2022-03-15 中国空气动力研究与发展中心计算空气动力研究所 Aircraft knowledge graph construction method, device, equipment and storage medium
CN114186690B (en) * 2022-02-16 2022-04-19 中国空气动力研究与发展中心计算空气动力研究所 Aircraft knowledge graph construction method, device, equipment and storage medium
WO2023092960A1 (en) * 2022-04-24 2023-06-01 之江实验室 Labeling method and apparatus for named entity recognition in legal document
CN116662582A (en) * 2023-08-01 2023-08-29 成都信通信息技术有限公司 Specific domain business knowledge retrieval method and retrieval device based on natural language
CN116662582B (en) * 2023-08-01 2023-10-10 成都信通信息技术有限公司 Specific domain business knowledge retrieval method and retrieval device based on natural language

Similar Documents

Publication Publication Date Title
CN111680511A (en) Military field named entity identification method with cooperation of multiple neural networks
CN111444721B (en) Chinese text key information extraction method based on pre-training language model
Wieting et al. Charagram: Embedding words and sentences via character n-grams
CN106980609A (en) A kind of name entity recognition method of the condition random field of word-based vector representation
CN106569998A (en) Text named entity recognition method based on Bi-LSTM, CNN and CRF
CN100405362C (en) New Chinese characters spoken language analytic method and device
CN110851599A (en) Automatic scoring method and teaching and assisting system for Chinese composition
CN111274327B (en) Entity and relation extraction method for unstructured table document
CN115761753A (en) Retrieval type knowledge prefix guide visual question-answering method fused with knowledge graph
CN114969275A (en) Conversation method and system based on bank knowledge graph
CN112784602A (en) News emotion entity extraction method based on remote supervision
Xie et al. Diverse distractor generation for constructing high-quality multiple choice questions
CN114580639A (en) Knowledge graph construction method based on automatic extraction and alignment of government affair triples
Sun et al. VCWE: visual character-enhanced word embeddings
CN113468887A (en) Student information relation extraction method and system based on boundary and segment classification
CN115063119A (en) Recruitment decision system and method based on adaptivity of recruitment behavior data
CN113934835B (en) Retrieval type reply dialogue method and system combining keywords and semantic understanding representation
CN112883172B (en) Biomedical question-answering method based on dual knowledge selection
Diao et al. Emotion cause detection with enhanced-representation attention convolutional-context network
Alipour et al. Learning bilingual word embedding mappings with similar words in related languages using GAN
Hua et al. A character-level method for text classification
CN116306653A (en) Regularized domain knowledge-aided named entity recognition method
CN111507103A (en) Self-training neural network word segmentation model using partial label set
Havrashenko et al. Analysis of text augmentation algorithms in artificial language machine translation systems
CN114579706B (en) Automatic subjective question review method based on BERT neural network and multi-task learning

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
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20200918

WD01 Invention patent application deemed withdrawn after publication