WordNet: a lexical database for English
Communications of the ACM
Question-answering by predictive annotation
SIGIR '00 Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval
Natural language question answering: the view from here
Natural Language Engineering
Automatic acquisition of hyponyms from large text corpora
COLING '92 Proceedings of the 14th conference on Computational linguistics - Volume 2
Yago: a core of semantic knowledge
Proceedings of the 16th international conference on World Wide Web
Answer type validation in question answering systems
RIAO '10 Adaptivity, Personalization and Fusion of Heterogeneous Information
Passage reranking for question answering using syntactic structures and answer types
ECIR'11 Proceedings of the 33rd European conference on Advances in information retrieval
Leveraging community-built knowledge for type coercion in question answering
ISWC'11 Proceedings of the 10th international conference on The semantic web - Volume Part II
Question analysis: how watson reads a clue
IBM Journal of Research and Development
Automatic knowledge extraction from documents
IBM Journal of Research and Development
Finding needles in the haystack: search and candidate generation
IBM Journal of Research and Development
Typing candidate answers using type coercion
IBM Journal of Research and Development
Hi-index | 0.00 |
Questions often explicitly request a particular type of answer. One popular approach to answering natural language questions involves filtering candidate answers based on precompiled lists of instances of common answer types (e.g., countries, animals, foods, etc.). Such a strategy is poorly suited to an open domain in which there is an extremely broad range of types of answers, and the most frequently occurring types cover only a small fraction of all answers. In this paper we present an alternative approach called TyCor, that employs soft filtering of candidates using multiple strategies and sources. We find that TyCor significantly outperforms a single-source, single-strategy hard filtering approach, demonstrating both that multi-source multi-strategy outperforms a single source, single strategy, and that its fault tolerance yields significantly better performance than a hard filter.