%0 Conference Paper %1 Li:2003 %A Li, Wei %A Srihari, Rohini %A Niu, Cheng %A Li, Xiaoge %B Proc. ACL 2003 Workshop on Multilingual Summarization and Question Answering %D 2003 %K question_answering speech %P 84-93 %T Question Answering on a Case Insensitive Corpus %X Most question answering (QA) systems rely on both keyword index and Named Entity (NE) tagging. The corpus from which the QA systems attempt to retrieve answers is usually mixed case text. However, there are numerous corpora that consist of case insensitive documents, e.g. speech recognition results. This paper presents a successful approach to QA on a case insensitive corpus, whereby a preprocessing module is designed to restore the case-sensitive form. The document pool with the restored case then feeds the QA system, which remains unchanged. The case restoration preprocessing is implemented as a Hidden Markov Model trained on a large raw corpus of case sensitive documents. It is demonstrated that this approach leads to very limited degradation in QA benchmarking (2.8%), mainly due to the limited degradation in the underlying information extraction support.

@inproceedings{Li:2003, abstract = {Most question answering (QA) systems rely on both keyword index and Named Entity (NE) tagging. The corpus from which the QA systems attempt to retrieve answers is usually mixed case text. However, there are numerous corpora that consist of case insensitive documents, e.g. speech recognition results. This paper presents a successful approach to QA on a case insensitive corpus, whereby a preprocessing module is designed to restore the case-sensitive form. The document pool with the restored case then feeds the QA system, which remains unchanged. The case restoration preprocessing is implemented as a Hidden Markov Model trained on a large raw corpus of case sensitive documents. It is demonstrated that this approach leads to very limited degradation in QA benchmarking (2.8%), mainly due to the limited degradation in the underlying information extraction support.}, added-at = {2007-12-14T02:42:23.000+0100}, author = {Li, Wei and Srihari, Rohini and Niu, Cheng and Li, Xiaoge}, biburl = {https://www.bibsonomy.org/bibtex/27f5c7977cedc4baf876d55e19e9e99b1/diego_ma}, booktitle = {Proc. ACL 2003 Workshop on Multilingual Summarization and Question Answering}, interhash = {dc531e7db11697f674851f5fe300015d}, intrahash = {7f5c7977cedc4baf876d55e19e9e99b1}, keywords = {question_answering speech}, pages = {84-93}, timestamp = {2007-12-14T02:42:23.000+0100}, title = {Question Answering on a Case Insensitive Corpus}, year = 2003 }