COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
Detecting action-items in e-mail
Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval
Investigation of question classifier in question answering
EMNLP '09 Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 2 - Volume 2
Hi-index | 0.00 |
Question classifiers are used within Question Answering to predict the expected answer type for a given question. This paper describes the first steps towards applying a similar methodology to identifying question classes in dialogue contexts, beginning with a study of questions drawn from the Enron email corpus. Human-annotated data is used as a gold standard for assessing the output from an existing, open-source question classifier (QA-SYS). Problem areas are identified and potential solutions discussed.