Answer extraction method and device

Abstract

The invention provides an answer extraction method and device. The answer extraction method is applied to an automatic question-answering system and includes the steps: dividing a received interrogative sentence into a plurality of participles and labeling the word class of each participle to generate a participle sequence; acquiring search keywords based on the participle sequence, calling a preset interface for executing a search operation, submitting the search keywords to the preset interface and generating an evidence corpus containing candidate answers according to search results; acquiring hot words in the search keywords and generating a hot word list; recognizing name entities in the evidence corpus according to the content of the interrogative sentence and generating a candidate answer initial set; determining a preset combined scoring mechanism according to the types of the name entities, respectively scoring the name entities in the candidate answer initial set, returning the name entity with the highest score as a correct answer to extract the answer for the interrogative sentence. By the method, answer extraction accuracy can be improved.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to an answer extraction method and device. Background technique [0002] With the development and popularization of the Internet, the information on the Internet is becoming more and more abundant, and people can find the information they want through search engines (such as Google, Baidu, etc.), for example, they can enter relevant keywords in the search box of the search engine and click Trigger the button to confirm the search, and then return the web page related to the keyword. But search engines have many deficiencies. For example, the user's search needs may be very complicated, and it is difficult to express them with a simple combination of several keywords, so that they cannot clearly express their own search needs. For another example, the search results are often many related web pages, documents, etc., and users need to spend a lot of time looking for the informa...

AI Technical Summary

Problems solved by technology

[0005] First of all, it ignores the role of search terms generated after question segmentation (also called question term) in extracting candidate answers, the frequency of appearance of question term in the evidence corpus, its own length, and its relationship with candidate answers. Features such as the syntactic relationship between have a very important role in judging candidate answers, but the above methods fail to distinguish the question terms according to the importance of the question terms;

[0006] Second, the role of the evidence corpus containing candidate answers in evaluating candidate answers is ignored;

[0007] Again, answer extraction is based on a single feature or a single method, which fails to solve the difficulty of answer extraction caused by syntactic and lexical diversity

Due to the diverse structures and complex syntactic structures of the evidence corpus containing answers, the effect of answer extraction based on only a certain feature, such as syntactic analysis features or a certain model, is not ideal.

Images