ACM Home Page
Please provide us with feedback. Feedback
MT-based Japanese-Enlish cross-language IR experiments using the TREC test collections
Full text PdfPdf (828 KB)
Source International Workshop on Information Retrieval with Asia Languages archive
Proceedings of the fifth international workshop on on Information retrieval with Asian languages table of contents
Hong Kong, China
Pages: 181 - 188  
Year of Publication: 2000
ISBN:1-58113-300-6
Author
Tetsuya Sakai  Computer Laboratory, University of Cambridge and Human Interface Laboratory, Corporate R&D Center, Toshiba Corporation
Sponsors
SIGIR: ACM Special Interest Group on Information Retrieval
SIGLINK: Hypertext, Hypermedia, and Web
SIGWEB: ACM Special Interest Group on Hypertext, Hypermedia, and Web
ACM Hong Kong Chapter : ACM Hong Kong Chapter Executive Committee
Publisher
ACM  New York, NY, USA
Bibliometrics
Downloads (6 Weeks): 4,   Downloads (12 Months): 14,   Citation Count: 4
Additional Information:

abstract   references   cited by   index terms   collaborative colleagues   peer to peer  

Tools and Actions: Review this Article  
DOI Bookmark: Use this link to bookmark this Article: http://doi.acm.org/10.1145/355214.355240
What is a DOI?

ABSTRACT

This paper evaluates the effectiveness of MT-based Japanese-English CLIR using a subcollection of the TREC test collections and two bilingual researchers to separately translate the TREC requests into Japanese. Our main findings are as follows: (1)With the aid of pseudo-relevance feedback, MT-based J-E CLIR can be as effective as “best-case” monolingual IR. In particular, although poor MT quality often leads to poor initial CLIR performance, pseudo-relevance feedback is useful for alleviating the harm; (2)The manual request translation process that is inherent in conventional CLIR performance evaluation can be a more dominant factor than query length and overall MT quality.


REFERENCES

Note: OCR errors may be found in this Reference List extracted from the full text article. ACM has opted to expose the complete List rather than only correct and linked references.

 
1
 
2
 
3
Oard, D. W.: Alternative Approaches for Cross-Language Text Retrieval, AAAI Spring Symposium on Cross-Language Text and Speech Retrieval Electronic Working Notes, 1997. Available from http://www.ece.umd.edu/ medlab/filter/sss/papers.
 
4
Gey, F. C., Jiang, H., Chen, A. and Larson, R. R.: Manual Queries and Machine Translation in Cross-language Retrieval and Interactive Retrieval with Cheshire II at TREC-7, TREC-7 Proceedings, 1999, pp. 527-540.
 
5
Oard, D. W. and Hackett, P.: Document Translation for Cross-Language Text Retrieval at the University of Maryland, TREC-6 Proceedings, 1998, pp. 687--696.
 
6
Sakai, T. et al.: A Study on English-to-Japanese / Japanese-to-English Cross-Language Information Retrieval using Machine Translation (in Japanese), IPSJ Transactions, Vol. 40, No. 11, 1999, pp. 4075--4086.
7
8
9
10
11
 
12
Jones, G. et al.: Exploring the use of Machine Translation Resources for English-Japanese Cross-Language Information Retrieval, Post-Conference Workshop on Machine Translation for Cross Language Information Retrieval at AAMT Machine Translation Summit VIII, 1999, pp. 15-22.
13
14
 
15
NTCIR: http://www.rd.nacsis.ac.jp/ "ntcadm/index-en.html
 
16
 
17
Kwok, K. L.: English-Chinese Cross-Language Retrieval based on a Translation Package, Post-Conference Workshop on Machine Translation for Cross Language InJormation Retrieval at AAMT Machine Translation Summit VIII, 1999.
 
18
Braschler, M., Peters, C. and Schauble, P.: Cross-Language Information Retrieval(CLIR) Track Overview, TREC.8 Proceedings, 2000.
 
19
Qu, Y. et al.: CLARIT TREC-8 CLIR Experiments, TREC-8 Proceedings, 2000.
 
20
Harmon, D.: What We Have Learned, and Not Learned, from TREC, BCS IRSG '2000 Proceedings, 2000, pp. 2-20.
 
21
Nakayama, K. and Kumano, A.: Collection of Dictionary Data through Internet Translation Service, AAMT Machine Translation Summit VIII Proceedings, 1999, pp. 586-592.
 
22
Sakai, T. et al.: Cross-Language Information Retrieval for NTCIR at Toshiba, NTCIR Workshop 1 Proceedings, 1999, pp. 137-144. http://www.rd.nacsis.ac.jp/-ntcadm/workshop/ OnlinePro ceedings/017-IR-Sakai.pdf
 
23
Robertson, S. E. and Walker, S.: Okapi/Keenbow at TREC-8, TREC-8 Proceedings, 2000.
 
24
Robertson, S. E. and Sparck Jones, K: Simple, Proven Approaches to Text Retrieval, Computer Laboratory, University of Cambridge, 1994.
 
25



Peer to Peer - Readers of this Article have also read: