Towards automatic question answering over social media by learning question equivalence patterns
WSA '10: Proceedings of the NAACL HLT 2010 Workshop on Computational Linguistics in a World of Social Media(2010)
摘要
Many questions submitted to Collaborative Question Answering (CQA) sites have been answered before. We propose an approach to automatically generating an answer to such questions based on automatically learning to identify "equivalent" questions. Our main contribution is an unsupervised method for automatically learning question equivalence patterns from CQA archive data . These patterns can be used to match new questions to their equivalents that have been answered before, and thereby help suggest answers automatically. We experimented with our method approach over a large collection of more than 200,000 real questions drawn from the Yahoo! Answers archive, automatically acquiring over 300 groups of question equivalence patterns. These patterns allow our method to obtain over 66% precision on automatically suggesting answers to new questions, significantly outperforming conventional baseline approaches to question matching.
更多查看译文
关键词
new question,question equivalence pattern,method approach,real question,unsupervised method,CQA archive data,conventional baseline approach,Collaborative Question Answering,large collection,main contribution,Towards automatic question answering,social media
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络