Knowledge base question-answering method fusing fact texts

Abstract

The invention relates to a knowledge base question-answering method fusing fact texts, and belongs to the field of natural language processing. According to the invention, natural language questions and candidate answer triples are analyzed respectively, entities, entity types and relationships in the triples are converted into fact texts; the natural language questions and the fact texts are mapped into numerical vectors in a low-dimensional semantic space through a pre-training language model BERT, and then cosine similarity is adopted for calculation and sorting, so that the knowledge basequestion-answering method model fusing the fact text is established; the model can learn the score relation between the natural language questions and the candidate answer triples so as to find the answer most similar to the semantics of the natural language questions in the knowledge base, and the question-answering method achieves a good effect.

Description

technical field [0001] The invention relates to a knowledge base question answering method for integrating factual texts, which belongs to the field of natural language processing. Background technique [0002] In recent years, with the rapid development of large-scale knowledge bases such as Freebase, DBpedia and YAGO, knowledge base question answering has attracted more and more researchers' attention. A typical knowledge base uses triples of "head entity-relationship-tail entity" as the basic unit to form a graph structure, and each triple is called a fact, such as (Yao Ming, people.person.place_of_birth, Shang Hai) It means "Yao Ming was born in Shanghai". There are thousands of triples in the knowledge base, and it is difficult for users to obtain valuable information. Knowledge base question answering can directly give answers to natural language questions based on the facts in the knowledge base, providing a way to directly access the knowledge base. For example, g...

AI Technical Summary

Problems solved by technology

These methods have achieved relatively good results, but knowledge base question answering is far from being solved. The main challenge is that there is a semantic gap between natural language questions and triples in the knowledge base. There are many expressions in the language, for example: the relationship "place_of_birth" in the triplet can be expressed in natural language "hometown", "born in", etc.; the entity name of the triplet is ambiguous, for example: Yao Ming and Dayaodu Represents the entity "Yao Ming"

Images