CN106970981B - Method for constructing relation extraction model based on transfer matrix - Google Patents
Method for constructing relation extraction model based on transfer matrix Download PDFInfo
- Publication number
- CN106970981B CN106970981B CN201710193366.9A CN201710193366A CN106970981B CN 106970981 B CN106970981 B CN 106970981B CN 201710193366 A CN201710193366 A CN 201710193366A CN 106970981 B CN106970981 B CN 106970981B
- Authority
- CN
- China
- Prior art keywords
- relationship
- training
- extraction model
- sentences
- distribution
- 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
Images
Classifications
-
- 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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a method for constructing a relation extraction model based on a transfer matrix. The method comprises the following steps: 1) selecting a basic relation extraction model M, the input of which is a sentence or a group of sentences describing the same pair of subjects and objects, and the output of which is a distribution p of the relations described by the input sentence or the input group of sentencesiAnd generating a vector representation s of the input sentence or the input set of sentences in the intermediate resulti(ii) a 2) According to siConstructing a transition matrix Ti(ii) a 3) Distributing the relation p output by the model MiMultiplying by the transition matrix TiAnd normalized to obtain a distribution o of possible annotated relations of the input sentence or of the input set of sentencesi(ii) a 4) Distribute o in this relationshipiAnd (4) fitting a noisy label as a target, training the basic relation extraction model M until a preset termination condition is reached, and obtaining a relation extraction model. The model can be free from the influence of noise, so that a better relation extraction effect can be obtained.
Description
Technical Field
The invention relates to a method for enhancing the resistance to noise data in the training process of a relationship extractor by utilizing a transfer matrix so as to improve the relationship extraction performance, belonging to the field of information extraction.
Background
With the development of information technology and internet, more and more text information can be acquired by people, and how to automatically construct a knowledge base by using a large amount of text information becomes a very important problem, so that a computer can better utilize information contained in the texts.
The knowledge base is generally composed of triples in the shape of (subject, predicate, object), for example, the triplet (china, capital, beijing) contains the knowledge that the capital of china is beijing. Thus, the process of automatically building a knowledge base is the process of automatically generating these triples. The relation extraction aims to solve the problem of how to automatically identify the relation between two examples (one example can be an entity such as 'China', and also can be time, numerical values and the like) described in the text, so that the triples are formed and filled in a knowledge base.
The data used by the relational extraction task is mainly constructed by a remote supervision method, namely, a word description which can possibly set forth some seed knowledge is automatically retrieved by using the seed knowledge, and then the noisy data is used for training a relational extraction model. The benefit of this approach is that a large amount of training data can be acquired at low cost, while the disadvantage is that a large portion of the data set will be noisy data. Also, manually labeled data may contain noise, for example, a person may miss labeling certain data because of carelessness, or may not be able to identify whether a sentence is describing a relationship because of insufficient domain knowledge. Since the noise data can have a significant effect on the training of the model, the quality of a relationship extraction model depends largely on its resistance to the noise data.
Disclosure of Invention
The invention aims to provide a method for constructing a relation extraction model with strong resistance to noise in training data. The input of the relation extraction task can be a sentence, namely, the relation between the target subject and the target object described by the input sentence is judged; or a set of sentences, each of which includes the target subject and the target object, that is, the relationship between the target subject and the target object is comprehensively judged in combination with the set of sentences. Assuming that | C | relationships are to be extracted, a | C | × | C | transition matrix T is constructed, where any element T in the matrix TijRepresenting the probability that the true relationship expressed by an input sentence (or a set of sentences input) is i, and it is incorrectly labeled as relationship j. Thus, given a basic relationship extraction model M, let its output relationship distribution be p, in trainingInstead of fitting p directly to the noisy label, the invention uses a transfer matrix T to convert p into a relationship distribution o to which it may be labeled, and uses o to fit the noisy label. Through the display modeling mode of the noise, the basic relation extractor M can be free from the influence of the noise during training, so that a better relation extraction effect can be obtained.
In order to achieve the purpose, the technical scheme of the invention is as follows:
(1) selecting a base relationship extraction model M that can generate a vector representation of an input sentence (or an overall vector representation of an input set of sentences), which outputs a distribution p of relationships described for a to-be-processed sentence i (or an ith set of sentences to be processed)iAnd generating a vector representation s of the sentence i to be processed (or the ith group of sentences to be processed) in the intermediate resulti。
(2) From the vector representation s of the current sentence i to be processed (or the ith set of sentences to be processed)iConstructing a transition matrix Ti. Wherein(i.e., matrix T)iRow j and column k) represents the probability that, for a sentence i to be processed (or an ith group of sentences to be processed), if its expressed relationship is j, it is incorrectly labeled k (where j and k are respectively associated with the matrix T)iCorresponding to the jth row and kth column). I.e. this transition matrix can be considered as a model of the noise pattern of an input sentence (or a set of sentences of the input).
(3) During training, the relation distribution p described by the input sentence (or the input sentence) predicted by the basic relation extraction model M is distributediMultiplication by a transfer matrix TiAnd normalized to obtain the distribution o of the relationships it may be labeled asiAnd let oiAnd (4) training by fitting a noisy label as a target until a preset termination condition is reached (for example, a pre-specified training round number is reached, or the extraction effect is improved slightly compared with that of the previous round, and the like).
(4) Through the step (3), the basic relationship extraction model M is fully trained. Due to the introduction of the transfer matrix, the influence of noise can be avoided when M is trained, and therefore a better relation extraction effect is achieved. In actual use, the prediction result of M is directly used, and a transfer matrix is not used.
In step (1), although the present invention defines that the basic relational extraction model M must be able to generate a vector representation of an input sentence or an overall vector representation of a group of input sentences, in practice most of the relational extraction models meet this requirement. For a traditional model based on a manually formulated feature template, the vector representation of the sentence may be a vector of extracted feature components; for neural network models, the layer in front of the output layer can generally be used as a vector representation of the sentence (other layers that can completely model the entire sentence can also be used). The overall vector representation of a group of sentences may be a weighted average of the vector representations of each sentence in the group, or may be a weighted average of the vector representations of each sentence after each sentence is further modeled by a recurrent neural network.
In step (2), s is represented from a sentence vector (or an overall vector representation of a set of sentences)iTo the transition matrix TiCan be represented by the following sub-formula:
wherein, wjkIs used to calculate the transition matrix TiIs at the jth row and kth column ofParameter (d) of (a) in the above formula wjkThe superscript T of (a) denotes transpose, b is the bias term. w is ajkAnd b is initialized randomly before training begins and updated by back propagation during training.
In addition, sometimes a model may generate a vector representation s for each relation/for an input sentence (or a set of input sentences)il. At this time, the matrix T is transferrediCan be obtained byGenerating an equation:
wherein s isijIs a vector representation of sentence i (or ith group of sentences) for relationship j, wkIs the weight vector of the relation k, the superscript T denotes the transposition, bjIs the bias term for relationship j. w is akAnd bjThe method is initialized randomly before training begins and updated through back propagation in the training process.
And, the vector representation of sentence i (or the overall vector representation of the ith group of sentences) siA new vector representation of sentence i (or an overall vector representation of the ith set of sentences) s 'may also be derived through several fully-connected layers'iAnd then generating a transfer matrix by using the formula.
In step (3), two different training modes may be used depending on whether the training data may be divided into several subsets of different noise levels.
1) If the training data is not further divisible according to the noise level, then it is necessary to use a progressive approach for training. The loss function at this time is as follows:
wherein N is the number of samples in the training set, one sample can be a sentence or a group of sentences,representing the output p of the basis relation extractor M for the samples iiThe error of the labeling fitted with noise,distribution o representing the relationship that a sample i may be labeled asiError of fitting a noisy annotation, Trace (T)i) Representing a transition matrix TiA is a real number between 0 and 1, betaIs a real number coefficient. The error loss can be used here with all piecewise-derivative functions that measure the difference between the predicted relationship distribution and the annotated relationship, including the cross entropy. Trace (T)i) Here a regularization term. Taking into account the transition matrix TiIs 1, and T is the case without noiseiShould be a unit array, then by controlling TiThe trace of (sum of diagonal elements) is equivalent to the noise modeling strength of the control transfer matrix. Large beta indicates the desired T of the inventioniApproaching a unit array, with a small (or negative) beta indicating that the invention encourages TiTo model the noise.
At the beginning of the training, α is set to 1 and β is set to a larger positive number, i.e., the present invention initially discourages modeling noise, but instead expects the fundamental relationship extraction model M to quickly learn the basic classification capability from noisy labels. Then, by gradually reducing α and β, the invention gradually emphasizes the importance of noise modeling during the training process, thereby reducing the influence of noise on the training of M. The optimization method used for training can be all gradient-based optimization methods including random gradient descent. And when the preset termination condition is reached, stopping training. The termination condition may be that the training reaches a certain number of rounds, or that the relationship extraction effect on the development set is not significantly improved any more, and the like.
2) If the training data can be divided into subsets (TD) according to the noise level from small to large1,TD2… …), the following loss function may be used:
where S is the number of subsets, NiIs a subset TDiThe number of samples in (2), a sample may be a sentence or a group of sentences,as a subset TDiDistribution of relationships into which the jth sample may be labeledoijError of fitting noisy annotations, betaiIs a subset TDiUp-transfer matrix TijThe regular term coefficients of the trace. Here, since the noise modeling strength of the transition matrix on each subset can be specified in advance by using the prior knowledge of the noise degrees of different subsets, l may not be usedosspTo directly optimize losso. In particular, for a subset with a low degree of noise, β may be setiFor a subset with a relatively large positive number but a high degree of noise, β may be setiNegative or relatively small positive.
The loss function loss, described above, can use all piecewise-derivative functions that measure the difference between the predicted relationship distribution and the labeled relationship, including the cross entropy. The optimization method can employ all gradient-based optimization methods including random gradient descent. During training, except training on all subsets directly, the training can also be performed on the subset with the minimum noise degree, and then the other subsets are gradually added into the training set from small to large according to the sequence of the noise degree. The termination condition of the training can be that the training reaches a certain number of rounds, or the relationship extraction effect on the development set is not obviously improved any more, and the like.
In the step (4), since the basic relationship extraction model M is actually fitted with the implicit real relationship distribution during training, the prediction result of the basic relationship extraction model M can be directly used during actual use.
Compared with the prior art, the invention has the following positive effects:
during training, the basic relationship extraction model M does not need to be directly fitted with a noisy label, but the distribution of the relationship described by the input sentence (or a group of input sentences) predicted by the model M is connected with the noisy label through a transfer matrix, so that the denoising effect is achieved. Compared with the existing method for directly fitting noisy labels with the output of M, the method disclosed by the invention has the advantages that the training of the basic relationship extraction model M is free from the influence of noise, the generation of biased models is avoided, and a better relationship extraction effect can be achieved.
Fig. 2 shows the effect of the present invention on the time of extracting objects (see the description of the following examples), and the extraction result is shown as an accuracy-recall curve, and the higher the curve is, the better the effect is. The data set can be divided into 3 subsets with different noise degrees, the effect of training on reliable subsets and then on unreliable subsets (training of the data sets in sequence) is obviously superior to the effect of training by mixing all the subsets together (mixed data set), and the noise in the data set has great influence on the training of the model. After the transfer matrix method disclosed by the invention is used, the relation extraction effect is further improved (training and transfer matrix are performed in sequence), and the method can effectively improve the anti-noise capability of the basic relation extraction model in the training process, so that the relation extraction effect is obviously improved.
Drawings
FIG. 1 is a block diagram of a relationship extraction method in an embodiment of the invention;
fig. 2 is a diagram illustrating an extraction effect of the relationship extraction method according to the embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it should be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention is based on the relation that the object is time in an open encyclopedia knowledge platform of the wiki data and the corpus of the wiki encyclopedia. It will be apparent to those skilled in the art that other sets of relationships and other corpora may be used in a particular implementation.
Specifically, there are 12 types of relationships to be extracted in this embodiment, including a birth date, a death date, an organization establishment date, a work publication date, a spacecraft launch date, and the like. The data set construction process is as follows:
1) collecting triplets in the wiki data containing relationships to be extracted, such as (centesimal, organization date, 1/2000);
2) for a triplet, find all sentences in wikipedia containing both the subject and object in the triplet, such as "the plum-shaped hydroarm creates a Baidu in 1 month and 1 day of 2000";
3) the present invention considers the sentences containing both the subject and the object of the triplet as the natural language description of the triplet. However, this assumption is incomplete and exceptions necessarily occur. The present invention then further assumes that the finer the temporal granularity mentioned in the sentence, the more likely it is that the present invention considers it to describe the triplet. For example, a sentence containing "1/2000" and "hundredths" is more likely to describe this triple (hundredths, organization establishment date, 1/2000) than a sentence containing only "2000" and "hundredths". According to this principle, the present invention divides the data set into three subsets of different degrees of reliability: including yearly-monthly days, including yearly-monthly, including yearly;
4) the invention takes out a part of the triples of the subset including the year, the month and the day as the test set, and the rest of the triples are used as the training set (sentences related to the triples of the test set in the other two subsets are also removed).
FIG. 1 is a diagram of a framework of a relationship extraction method based on a transition matrix according to an embodiment of the present invention;
step 1: a vector representation of the sentence to be processed is generated.
For an input sentence, the present invention first generates a vector representation thereof. Here, the present invention first converts each word in the sentence into a corresponding word vector, and then generates a vector representation of the sentence through a Convolutional Neural network (see Zeng Daojian, Liu Kang, Chen Yubo, Zhao jun.
Step 2: a distribution of the relationships described by the sentence is generated using a base relationship extractor.
Obtaining a vector representation of a sentencesiThen, the invention generates the predicted relationship distribution through the softmax classifier, and the concrete formula is as follows:
wherein p isijIs the distribution p of the relationships described by the sentence iiItem j of (d), representing the probability that sentence i describes relationship j, wjIs the weight vector of the relationship j, wjThe superscript T of (a) denotes transpose.
And step 3: modeling noise to generate transfer matrix Ti。
Since there is only one vector representation for a sentence, the present invention generates the transition matrix T using the following formula mentioned in the methods sectioni:
And 4, step 4: distribution of relationships p using predictionsiAnd a transfer matrix TiGenerating a distribution o of relationships that the sentence may be tagged toi:
Wherein o isijRepresents oiAnd the second formula is p'iThe normalization is performed such that it satisfies the properties of the probability distribution.
During training, the invention trains 15 rounds on the subset of 'including year, month and day', then trains 15 rounds after adding the subset of 'including year and month', and trains 15 rounds after adding the subset of 'including year'. Wherein the regularization coefficients (coefficients of the traces of the transfer matrix) of the three subsets "including year, month and day", "including year" and "including year" are 0.01, -0.01 and-0.1, respectively.
Fig. 2 shows the relationship extraction effect of the method, and the evaluation index is an accuracy-recall curve. Specifically, the relational extraction results are ranked from high to low according to the confidence coefficient output by the relational extractor, the accuracy and the recall ratio are calculated for each extraction result and the result higher than the confidence coefficient of each extraction result in sequence, and finally an accuracy-recall ratio curve is drawn, wherein the higher the curve is, the better the relational extraction effect is. The calculation method of the accuracy and the recall rate comprises the following steps:
it can be seen from the figure that, under the condition of not adding a transition matrix, different data subsets are sequentially added into a training set for training according to the sequence of the noise degrees from small to large (the data sets are sequentially trained), which is better than the training effect directly on all the data sets (mixed data sets), and shows that the noise in the data sets has a significant influence on the effect of the trained relation extraction model. After the transfer matrix is added (training and transferring the matrix in sequence), the relation extraction effect is obviously improved compared with that before the transfer matrix is added, and the method can effectively model noise, so that a basic relation extractor is free from the influence of the noise, and a better relation extraction effect is obtained.
In summary, in the embodiment of the present invention, a reliable relationship extractor for extracting a relationship that an object is time is constructed based on wiki data and wikipedia. In the process of training the extractor, the method provided by the invention can effectively avoid the influence of noise in data on the relation extractor, thereby training the relation extractor with better effect.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is intended to include such modifications and variations.
Claims (8)
1. A method for constructing a relation extraction model based on a transfer matrix comprises the following steps:
1) selecting a basic relation extraction model M, the output of which is a distribution p of the relations described by the input sentence iiAnd generating a vector representation s of the input sentence i in the intermediate resulti;
2) From the vector representation s of the input sentence iiConstructing a transition matrix Ti(ii) a Wherein the content of the first and second substances,is a matrix TiThe jth row and kth column of (a), representing the probability that the input sentence i expresses a relationship of j, but is incorrectly labeled as k;
3) the relation distribution p output by the basic relation extraction model MiMultiplying by the transition matrix TiAnd normalizing to obtain the distribution o of the relationship which the input sentence may be labeled intoi;
4) Distribute o in this relationshipiFitting a noisy label as a target, and training the basic relationship extraction model M until a preset termination condition is reached to obtain a relationship extraction model;
the method for training the basic relationship extraction model M comprises the following steps: a) if the training data cannot be further divided according to the noise level, the loss function used in the training is
Wherein N is a sample of training dataThe total number, a sample is a sentence or a group of sentences,representing a relationship distribution p output by a basis relationship extractor M for a sample iiThe error of the labeling fitted with noise,representing a distribution of relationships o to which a sample i may be labelediError of fitting noisy annotations, Trace (T)i) Representing the transition matrix T corresponding to the sample iiα is a real number between 0 and 1, β is a real number coefficient; b) if the training data can be further divided into subsets according to the degree of noise, the loss function used in the training isWhere S is the total number of subsets, NiIs a subset TDiThe number of samples of (a) to (b),as a subset TDiIs marked as a distribution o of relationshipsijError of fitting noisy annotations, betaiIs a subset TDiUp-transfer matrix TijThe regular term coefficients of the trace.
2. The method of claim 1, wherein if the fundamental relationship extraction model M generates only one vector representation s for an input sentence iiThen it is statedWherein, wjkIs used to calculate the transition matrix TiIs at the jth row and kth column ofIs determined by the parameters of (a) and (b),is wjkB is a bias term, wjkAnd b are updated by back-propagation during training, | C | is the size of the set of relationships to be extracted.
3. The method of claim 1, wherein if the basic relationship extraction model M generates a vector representation s for each relationship/for an input sentence iilThen it is statedWherein s isijIs a vector representation of the input sentence i for the relation j, wkIs a weight vector for the relationship k,is wkTranspose of (b)jIs a bias term of the relationship j, wkAnd bjUpdated by back-propagation during the training process, | C | is the size of the set of relationships to be extracted.
4. The method of claim 1, wherein the vector can be further represented as siAfter processing of a plurality of full connection layers, a new vector representation s 'of sentence i is obtained'iThen according to s'iConstructing the transfer matrix Ti。
5. A method for constructing a relation extraction model based on a transfer matrix comprises the following steps:
1) selecting a basic relationship extraction model M, which is input as a set of sentences describing the same pair of subject and object, and which is output as a distribution p of the relationships described by the set of sentencesiAnd generating an overall vector representation s of the input set of sentences in the intermediate resulti;
2) From the global vector representation s of the set of sentencesiConstructing a transition matrix Ti(ii) a Wherein the content of the first and second substances,is a matrix TiThe jth row and kth column of (a), indicating a probability that the set of sentences expresses a relationship of j, but is incorrectly labeled as k;
3) the relation distribution p output by the basic relation extraction model MiMultiplying by the transition matrix TiAnd normalizing to obtain the distribution o of the possible labeled relations of a group of input sentencesi;
4) Distribute o in this relationshipiFitting a noisy label as a target, and training the basic relationship extraction model M until a preset termination condition is reached to obtain a relationship extraction model;
the method for training the basic relationship extraction model M comprises the following steps: a) if the training data cannot be further divided according to the noise level, the loss function used in the training isWherein N is the total number of samples of the training data, one sample can be a sentence or a group of sentences,representing a relationship distribution p output by a basis relationship extractor M for a sample iiThe error of the labeling fitted with noise,representing a distribution of relationships o to which a sample i may be labelediError of fitting noisy annotations, Trace (T)i) Representing the transition matrix T corresponding to the sample iiα is a real number between 0 and 1, β is a real number coefficient; b) if the training data can be further divided into subsets according to the degree of noise, the loss function used in the training isWhere S is the total number of subsets, NiIs a subset TDiThe number of samples of (a) to (b),as a subset TDiIs marked as a distribution o of relationshipsijError of fitting noisy annotations, betaiIs a subset TDiUp-transfer matrix TijThe regular term coefficients of the trace.
6. The method of claim 5, wherein if the fundamental relationship extraction model M generates only one vector representation s for the set of sentencesiThen it is statedWherein, wjkIs used to calculate the transition matrix TiIs at the jth row and kth column ofIs determined by the parameters of (a) and (b),is wjkB is a bias term, wjkAnd b are updated by back-propagation during training, | C | is the size of the set of relationships to be extracted.
7. The method of claim 5, wherein if the fundamental relationship extraction model M generates a vector representation s for each relationship/for the set of sentencesilThen it is statedWherein s isijIs a vector representation, w, of the set of sentences for the relationship jkIs a weight vector for the relationship k,is wkTranspose of (b)jIs a bias term of the relationship j, wkAnd bjUpdated by back-propagation during the training process, | C | is the size of the set of relationships to be extracted.
8. The method of claim 5, wherein the vector can be further represented as siAfter several full connected layers processing, a new overall vector representation s 'of the set of sentences is obtained'iThen according to s'iConstructing the transfer matrix Ti。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710193366.9A CN106970981B (en) | 2017-03-28 | 2017-03-28 | Method for constructing relation extraction model based on transfer matrix |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710193366.9A CN106970981B (en) | 2017-03-28 | 2017-03-28 | Method for constructing relation extraction model based on transfer matrix |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106970981A CN106970981A (en) | 2017-07-21 |
CN106970981B true CN106970981B (en) | 2021-01-19 |
Family
ID=59336048
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710193366.9A Active CN106970981B (en) | 2017-03-28 | 2017-03-28 | Method for constructing relation extraction model based on transfer matrix |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106970981B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110276066B (en) * | 2018-03-16 | 2021-07-27 | 北京国双科技有限公司 | Entity association relation analysis method and related device |
CN111914091B (en) * | 2019-05-07 | 2022-10-14 | 四川大学 | Entity and relation combined extraction method based on reinforcement learning |
CN110489529B (en) * | 2019-08-26 | 2021-12-14 | 哈尔滨工业大学(深圳) | Dialogue generating method based on syntactic structure and reordering |
CN110795527B (en) * | 2019-09-03 | 2022-04-29 | 腾讯科技(深圳)有限公司 | Candidate entity ordering method, training method and related device |
CN113672727B (en) * | 2021-07-28 | 2024-04-05 | 重庆大学 | Financial text entity relation extraction method and system |
CN116542250B (en) * | 2023-06-29 | 2024-04-19 | 杭州同花顺数据开发有限公司 | Information extraction model acquisition method and system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2011118526A (en) * | 2009-12-01 | 2011-06-16 | Hitachi Ltd | Device for extraction of word semantic relation |
CN103678703A (en) * | 2013-12-30 | 2014-03-26 | 中国科学院自动化研究所 | Method and device for extracting open category named entity by means of random walking on map |
CN104035975A (en) * | 2014-05-23 | 2014-09-10 | 华东师范大学 | Method utilizing Chinese online resources for supervising extraction of character relations remotely |
CN106354710A (en) * | 2016-08-18 | 2017-01-25 | 清华大学 | Neural network relation extracting method |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9858261B2 (en) * | 2014-06-23 | 2018-01-02 | International Business Machines Corporation | Relation extraction using manifold models |
-
2017
- 2017-03-28 CN CN201710193366.9A patent/CN106970981B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2011118526A (en) * | 2009-12-01 | 2011-06-16 | Hitachi Ltd | Device for extraction of word semantic relation |
CN103678703A (en) * | 2013-12-30 | 2014-03-26 | 中国科学院自动化研究所 | Method and device for extracting open category named entity by means of random walking on map |
CN104035975A (en) * | 2014-05-23 | 2014-09-10 | 华东师范大学 | Method utilizing Chinese online resources for supervising extraction of character relations remotely |
CN106354710A (en) * | 2016-08-18 | 2017-01-25 | 清华大学 | Neural network relation extracting method |
Non-Patent Citations (3)
Title |
---|
Learning with Noise:Enhance Distantly Supervised Relation Extraction with Dynamic Transition Matrix;Bingfeng luo et al;《https://www.researchgate.net/publication/318737364_Learning_with_Noise_Enhance_Distantly_Supervised_Relation_Extraction_with_Dynamic_Transition_Matrix》;20170131;1-10 * |
中文实体关系抽取研究;牟晋娟等;《计算机工程与设计》;20091231;第30卷(第15期);3587-3590 * |
基于核方法的中文实体关系抽取研究;黄瑞红等;《中文信息学报》;20080930;第22卷(第5期);102-108 * |
Also Published As
Publication number | Publication date |
---|---|
CN106970981A (en) | 2017-07-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106970981B (en) | Method for constructing relation extraction model based on transfer matrix | |
CN108984745B (en) | Neural network text classification method fusing multiple knowledge maps | |
CN108363753B (en) | Comment text emotion classification model training and emotion classification method, device and equipment | |
CN107832400B (en) | A kind of method that location-based LSTM and CNN conjunctive model carries out relationship classification | |
CN106886543B (en) | Knowledge graph representation learning method and system combined with entity description | |
CN104834747B (en) | Short text classification method based on convolutional neural networks | |
WO2022267976A1 (en) | Entity alignment method and apparatus for multi-modal knowledge graphs, and storage medium | |
CN111143576A (en) | Event-oriented dynamic knowledge graph construction method and device | |
CN113239186B (en) | Graph convolution network relation extraction method based on multi-dependency relation representation mechanism | |
CN110334219A (en) | The knowledge mapping for incorporating text semantic feature based on attention mechanism indicates learning method | |
WO2020063092A1 (en) | Knowledge graph processing method and apparatus | |
CN110222178A (en) | Text sentiment classification method, device, electronic equipment and readable storage medium storing program for executing | |
CN110674850A (en) | Image description generation method based on attention mechanism | |
CN107220220A (en) | Electronic equipment and method for text-processing | |
WO2019196210A1 (en) | Data analysis method, computer readable storage medium, terminal device and apparatus | |
CN103207855A (en) | Fine-grained sentiment analysis system and method specific to product comment information | |
CN111104509B (en) | Entity relationship classification method based on probability distribution self-adaption | |
CN111027309B (en) | Entity attribute value extraction method based on two-way long-short-term memory network | |
CN109214562A (en) | A kind of power grid scientific research hotspot prediction and method for pushing based on RNN | |
CN112836051B (en) | Online self-learning court electronic file text classification method | |
US20220036003A1 (en) | Methods and systems for automated detection of personal information using neural networks | |
CN114722820A (en) | Chinese entity relation extraction method based on gating mechanism and graph attention network | |
CN111368082A (en) | Emotion analysis method for domain adaptive word embedding based on hierarchical network | |
CN114925205B (en) | GCN-GRU text classification method based on contrast learning | |
CN108920446A (en) | A kind of processing method of Engineering document |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
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 |