Qualitative dimensions in question answering: extending the definitional QA task
Lucian Vlad Lita, Andrew Hazen Schlaikjer, WeiChang Hong, Eric Nyberg · 2005
Current question answering tasks handle definitional questions by seeking answers which are factual in nature. While factual answers are a very important component in defining entities, a wealth of qualitative data is ignored. In this incipient work, we define qualitative dimensions (credibility, sentiment, contradictions, temporal etc.) for evaluating answers to definitional questions and we explore potential benefits to users. These qualitative dimensions are leveraged to uncover indirect and implicit answers and can help satisfy the user’s information need.