A Sentence-Level Entity and Relation Joint Extraction Method

Abstract

The invention discloses a joint extraction technology of entity and relation based on neural network. The technology includes the following steps: 1) Take the sentence as input to obtain the representation vector of each word, which is concatenated by the word embedding representation and character-level word embedding representation; 2) use the expanded convolutional neural network to Encode the context information of each word, and extract features containing context information for each word; 3) Treat entity recognition as a sequence labeling problem, and use linear chain CRF to jointly model the entity label sequence; when predicting, use the Viterbi algorithm to calculate the probability The largest entity tag sequence to realize entity recognition; 4) Obtain the feature representation of the entity from the feature representation of the words that make up the entity, construct the relationship candidate by arranging the entities in pairs, and use the double affine transformation to judge the identity of each relationship candidate relationship, to achieve relationship extraction.

Description

technical field [0001] The invention relates to the application of a neural network method in entity recognition and relation extraction technology, in particular to a sentence-level entity and relation joint extraction method. Background technique [0002] Entity and relationship extraction is an important subtask in information extraction, in which entity extraction or Named Entity Recognition (NER for short) refers to identifying named entity mentions from text and referring to them Entities are classified, and relation extraction (Relation Extraction, referred to as RE) refers to identifying a certain semantic relationship between entities from text. Entity and relationship extraction provide important technical support for many high-level applications of natural language processing, such as knowledge graphs, question answering systems, search engines, etc. [0003] The traditional method solves the problem of entity and relationship extraction in a pipelined manner. Th...

AI Technical Summary

Problems solved by technology

However, the languages ​​supported by these NLP tools are usually limited and may not be reliable enough to allow error propagation

[0006] 2) Most of these methods use recurrent neural network (RNN), especially bidirectional long-term short-term memory network (Bi-LSTM) to model the input sequence, but due to the limitation of sequence calculation, RNN cannot perform parallel calculation at the sequence element level, so it cannot Make full use of the parallel computing power of GPU

Therefore, these neural network methods are not computationally efficient

[0007] 3) These methods do not fully consider the directionality of the relationship, most of which only regard the relationship as an undirected relationship, and only a few methods take the directionality of the relationship into account, but they do not make full use of it

Images