Question and Answer Classifier for closed domain Interactive Question Answering

• Academic year of topic announcement: 2008/2009
• Thesis type: diploma thesis
• Thesis language: angličtina
• Department: Institute of Formal and Applied Linguistics (32-UFAL)
• Supervisor: doc. RNDr. Markéta Lopatková, Ph.D.
• Author: hidden - assigned and confirmed by the Study Dept.
• Date of registration: 07.11.2008
• Date of assignment: 07.11.2008
• Date and time of defence: 14.09.2009 00:00
• Date of electronic submission: 14.09.2009
• Date of proceeded defence: 14.09.2009
• Opponents: Mgr. Pavel Schlesinger

Guidelines

Question answering (QA) constitutes a modern and exciting information retrieval topic, especially as an alternative to document retrieval. Users formulate their information needs in the form of natural-language questions and the QA system returns brief answer strings extracted from a collection of text documents, taking advantage of the fact that answers to specific questions are often concentrated in fragments of text documents. A general QA system includes four main components: Question Analysis, Information Retrieval, Answer Extraction and Answer Selection. One of the most important processes of those listed is the Question Classification in Question Analysis. It identifies the target of intension in a given question to determine the type of sought-after answer.

The goal of the thesis is the question types and answer types classification of a given user-collected data using machine learning classifiers to help improve the performance of a closed-domain QA library system.

References

X. Li and D. Roth. 2002. Learning question classifiers. In Proceedings of the 19th International Conference on Computational Linguistics (COLING 2002), pages 556?562.

K. Hacioglu and W. Ward. 2003. Question classification with support vector machines and error correcting codes. In Proceedings of HLT-NACCL 2003.

D. Zhang and W. S. Lee. 2003. Question classification using support vector machines. In Proceedings of the 26th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 26?32.

J. Suzuki, H. Taira, Y. Sasaki, and E. Maeda. 2003b. Question classification using HDAG kernel. In The ACL 2003 Workshop on Multilingual Summarization and Question Answering.

Sunblad, Hakan. 2007. A Re-examination of Question Classification. In Proceedings of the 16th Nordic Conference of Computational Linguistics NODALIDA-2007, pages 394-397.

Marius Pasca. 2003. Open-Domain Question Answering from Large Text Collections. CSLI Publication, Center for the Study of Language and Information, 157p.

D. Moldovan, S. Harabagiu, R. Mihalcea, R. Goodrum, R. Girju, V. Rus. Lasso: A Tool for Surfing the Answer Net. In Proceedings of the 8th Text REtrieval Conference (TREC-8), 1999.