Information element joint extraction method and system based on deep learning

Abstract

The invention relates to an information element joint extraction method and system based on deep learning. The method comprises the following steps of: converting an input target text into a target word vector representation by utilizing a pre-training language model and a bidirectional long-short-term memory network; enumerating all text spans of each sentence in the target word vector, and obtaining a target text span vector representation based on the target word vector representation; constructing a text span graph network corresponding to the co-reference relationship, the entity relationship and the event structure relationship, and transmitting and updating text span vector representation; and performing multi-task classification on each updated text span vector representation. According to the method, the target text is converted into the target word vector representation, and the text span vector representation integrating a local context and a global context can be learned, so that span graph networks corresponding to different relationships can be constructed and the text span vector representation is updated, and then task classification of the text span vector representation is realized; and the association degree among the tasks is improved, so that the performance of the tasks is improved.

Description

technical field [0001] The present invention relates to the technical field of natural language processing, in particular to a model for joint extraction of information elements based on deep learning. Background technique [0002] Information extraction technology is mainly used to extract various specified structured information (such as entities, relationships, events) and integrate these information at different levels. Its core content includes named entity recognition (Named EntityRecognition, NER), relation extraction (Relation Extraction), event extraction (Event Detection). [0003] (1) Named entity recognition refers to the recognition of character strings in text that represent objective existence in the real world and have specific names. It is necessary to identify the boundaries of the entity and determine the entity type. [0004] (2) Relational extraction, which usually refers to identifying the semantic relationship that exists between two entities. Iden...

AI Technical Summary

Problems solved by technology

In order to avoid the cascading errors caused by the pipeline mode, research in recent years has made some attempts on the joint model of the above extraction tasks, but most of them only rely on the LSTM of the embedding layer to realize the text span representation information sharing of different extraction tasks , the degree of correlation between the tasks is not high

Images