Abstract
The development of question and answer technology is of great significance to the rapid processing of Internet information. The selection of candidate answer sentences is an important part of the question and answer (QA) system, and its accuracy will directly affect the effect of answer extraction. To solve the problem of insufficient feature interaction between question and answer sentences, this paper proposes a candidate answer sentence selection method based on Multi-granularity attention. The method used a Bi-directional Long Short-Term Memory (BLSTM) network to encode the words in the sentence, and then use the attention mechanism to obtain the relationship between sentences and words, words and words. The result of experiments on DBQA dataset show that our method can learn the relationship between question and answer sentences from different granularity of sentences and words, and improve the selection effect of answer sentences.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
