Open-ended language communications introduce an enormous challenge in automatic understanding and modeling of human language. In particular, Community Question Answering (cQA) forums, such as Quora and Stackoverflow contain millions of open-ended questions and answers. The proliferation of questions and answers in such platforms motivates the ability to automatically find relevant questions to a new question, Question Retrieval, and relevant answers among existing answers, Answer Selection. From the semantic perspective, there are two major factors that make these tasks challenging: First, cQA forums contain open-domain and non-factoid questions and answers, resulting in high variance question and answer quality. Second, a considerable fraction of questions and answers are long and contain several dozen to several hundred words, resulting in difficulty of encoding questions and answers to be understood by computers. We have developed neural network approaches and demonstrated their effectiveness on the cQA tasks for ranking a list of questions or answers for a given question.
Neural-based Approaches for Ranking in Community Question Answering
In Proceedings of NAACL-HLT Workshop on Semantic Evaluation, pp. 753-760, San Diego, California, USA, June 2016.
Neural Attention for Learning to Rank Questions in Community Question Answering
In Proc. COLING, pp. 1734-1745, Osaka, Japan, December 2016.
Learning Semantic Relatedness in Community Question Answering Using Neural Models
In Proceedings of ACL Workshop on Representation Learning for NLP, Berlin, Germany, August 2016.
SemEval-2016 Task 3: Community Question Answering
In Proceedings of NAACL-HLT Workshop on Semantic Evaluation, pp. 537-557, San Diego, California, USA, June 2016.
VectorSLU: A Continuous Word Vector Approach to Answer Selection in Community Question Answering Systems
In Proc. SemEval, pp. 282-287, Denver, Colorado, USA, June 2015.
SemEval-2015 Task 3: Answer Selection in Community Question Answering
In Proc. SemEval, pp. 269-281, Denver, Colorado, USA, June 2015.