Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

An analysis of question processing of English and Chinese for the NTCIR 5 cross-language question answering task

Judge, John, Guo, Yuqing, Jones, Gareth J.F. orcid logoORCID: 0000-0003-2923-8365 and Wang, Bin (2005) An analysis of question processing of English and Chinese for the NTCIR 5 cross-language question answering task. In: NTCIR Workshop 5 Meeting The 5th NTCIR Workshop Meeting 2005, 6-9 December 2005, Tokyo, Japan.

Abstract
An important element in question answering systems is the analysis and interpretation of questions. Using the NTCIR 5 Cross-Language Question Answering (CLQA) question test set we demonstrate that the accuracy of deep question analysis is dependent on the quantity and suitability of the available linguistic resources. We further demonstrate that applying question analysis tools developed on monolingual training materials to questions translated Chinese-English and English-Chinese using machine translation produces much reduced effectiveness in interpretation of the question. This latter result indicates that question analysis for CLQA should primarily be conducted in the question language prior to translation.
Metadata
Item Type:Conference or Workshop Item (Paper)
Event Type:Workshop
Refereed:Yes
Uncontrolled Keywords:question analysis; question translation; cross-language question answering;
Subjects:Computer Science > Machine translating
DCU Faculties and Centres:Research Initiatives and Centres > Centre for Digital Video Processing (CDVP)
Research Initiatives and Centres > National Centre for Language Technology (NCLT)
DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Publisher:National Institute of Informatics
Official URL:http://research.nii.ac.jp/ntcir/workshop/OnlinePro...
Copyright Information:©2005 National Institute of Informatics (NII)
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
ID Code:15294
Deposited On:12 Mar 2010 13:09 by DORAS Administrator . Last Modified 25 Oct 2018 13:11
Documents

Full text available as:

[thumbnail of judge_et_al_05b.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
419kB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record