Mail

Supporting Human Answers for Advice-Seeking Questions in CQA Sites

Publication
Mar 21, 2016
Abstract

In many questions in Community Question Answering sites users look for the advice or opinion of other users who might oer diverse perspectives on a topic at hand. The novel task we address is providing supportive evidence for human answers to such questions, which will potentially help the asker in choosing answers that t her needs.We present a support retrieval model that ranks sentences from Wikipedia by their presumed support for a human answer. The model outperforms a state-of-the-art textual entailment system designed to infer factual claims from texts. An important aspect of the model is the integration of relevance oriented and support oriented features.

  • European Conference on Information Retrieval (ECIR 2016)
  • Conference/Workshop Paper

BibTeX