Knowledge graph construction method for massive conference texts

Abstract

The invention discloses a knowledge graph construction method for massive conference texts. The method specifically comprises the following three steps: 1) conference summary extraction: firstly extracting common attributes of each summary document based on a summary template, and then extracting entities and relationships in each summary document based on joint modeling; 2) conference content extraction: firstly extracting common attributes of each conference content document based on a conference content template, then segmenting the non-structured document, and taking each segment as an entity in the knowledge graph; and (3) relation extraction between the conference summary and the conference content: by establishing the relation between the conference summary and the conference content, establishing a relation with each piece of conference content by each conference summary, and extracting the relation by adopting a model based on semantic matching in the process. According to the method, model training is completed based on a self-built data set, a knowledge graph based on conference text data can be constructed, and retrieval of conference information can be completed based on the knowledge graph.

Description

technical field

[0001] The present invention relates to the field of natural language processing, in particular to a method for constructing knowledge graphs for massive meeting texts. Background technique

[0002] In recent years, the society has increasingly realized that the traditional search engine retrieval model can no longer meet the needs of complex information, and it is suggested to provide additional enhanced services for complex search tasks according to the characteristics of complex information. This is the consensus of mainstream search engine companies Google, Bing, and Baidu. Automated Question Answering System is a more advanced next-generation search engine that returns simple, direct and real-time answers instead of sorted lists with hyperlinks. A knowledge graph is a semantic network containing a large number of concepts and relationships, which is interpretable. In recent years, due to its excellent knowledge representation ability, it has been widel...

Images