Answering Complex Questions Using Open Information Extraction

Tushar Khot, Ashish Sabharwal, Peter Clark
2017 Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)  
While there has been substantial progress in factoid question-answering (QA), answering complex questions remains challenging, typically requiring both a large body of knowledge and inference techniques. Open Information Extraction (Open IE) provides a way to generate semi-structured knowledge for QA, but to date such knowledge has only been used to answer simple questions with retrievalbased methods. We overcome this limitation by presenting a method for reasoning with Open IE knowledge,
more » ... ng more complex questions to be handled. Using a recently proposed support graph optimization framework for QA, we develop a new inference model for Open IE, in particular one that can work effectively with multiple short facts, noise, and the relational structure of tuples. Our model significantly outperforms a state-of-the-art structured solver on complex questions of varying difficulty, while also removing the reliance on manually curated knowledge. 7 w(t, h) =| tok (t) \ tok (h) | / | tok (h) | 313
doi:10.18653/v1/p17-2049 dblp:conf/acl/KhotSC17 fatcat:pa7o4kqbmjgwpke5r6reu7lgy4