Lexico-semantic pattern matching as a companion to parsing in text understanding
HLT '91 Proceedings of the workshop on Speech and Natural Language
A maximum entropy approach to natural language processing
Computational Linguistics
Building a question answering test collection
SIGIR '00 Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval
Performance issues and error analysis in an open-domain question answering system
ACM Transactions on Information Systems (TOIS)
Methods for automatically evaluating answers to complex questions
Information Retrieval
Splitting complex temporal questions for question answering systems
ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
Semantic passage segmentation based on sentence topics for question answering
Information Sciences: an International Journal
Document retrieval in the context of question answering
ECIR'03 Proceedings of the 25th European conference on IR research
Enhanced question answering with combination of pre-acquired answers
AIRS'05 Proceedings of the Second Asia conference on Asia Information Retrieval Technology
A LF based answer indexing method for encyclopedia question-answering system
AIRS'05 Proceedings of the Second Asia conference on Asia Information Retrieval Technology
Fine-Grained named entity recognition using conditional random fields for question answering
AIRS'06 Proceedings of the Third Asia conference on Information Retrieval Technology
Finding more trustworthy answers: Various trustworthiness factors in question answering
Journal of Information Science
Hi-index | 0.00 |
This paper describes how questions can be characterized for question answering (QA) along different facets and focuses on questions that cannot be answered directly but can be divided into simpler ones so that they can be answered directly using existing QA capabilities. Since individual answers are composed to generate the final answer, we call this process as compositional QA. The goal of the proposed QA method is to answer a composite question by dividing it into atomic ones, instead of developing an entirely new method tailored for the new question type. A question is analyzed automatically to determine its class, and its sub-questions are sent to the relevant QA modules. Answers returned from the individual QA modules are composed based on the predetermined plan corresponding to the question type. The experimental results based on 615 questions show that the compositional QA approach outperforms the simple routing method by about 17%. Considering 115 composite questions only, the F-score was almost tripled from the baseline.