Answer selection method for question and answer system

Abstract

The invention discloses an answer selection method for a question and answer system. A hierarchical length adaptive neural network structure is adopted to generate sentence distributed representationof questions and answers. The method aims to extract high-quality sentence features by adopting different neural feature extractors according to the lengths of input sentences. The method comprises the following steps: firstly, generating a word distributed representation for each word in an input statement by connecting a fixed word insert and a fine-tuning word insert; then, using a feature extractor based on BiLSTM for short sentences, and using a feature extractor based on Transformer for long sentences; and finally, generating a sentence vector representation for measuring the correlationbetween the question and the candidate answer by using an attention pooling layer considering the interaction between the question and the answer sentence. Experimental results show that the answer selection model based on the length adaptive neural network provided by the invention can be greatly improved in the aspects of MAP and MRR compared with the most advanced baseline.

Description

technical field [0001] The invention relates to the technical field of question answering systems, in particular to an answer selection method for question answering systems. Background technique [0002] Answer selection in a computer question answering system is to select the correct answer to a question from some candidate answers. Existing methods mainly try to generate high-quality sentence distributed representations for questions and candidate answers, and then these distributed representations will be used to measure candidate The correlation between the answer and the question, and then select the candidate answer with the highest correlation as the correct answer to return. Most of the existing methods use the recurrent neural network (RNN) to achieve good performance, but the inventors are in In use, it is found that RNN uses the same feature extractor to process all question and answer sentences, regardless of the sentence length. These methods often encounter th...

AI Technical Summary

Problems solved by technology

[0003] In view of this, the purpose of the present invention is to propose an answer selection method for question answering systems, which solves the problem that the answer selection methods in existing question answering systems ignore the length of sentences

Images