ICLEF 2001 at Maryland: Comparing word-for-word gloss and MT

Jianqiang Wang; Douglas W. Oard

ICLEF 2001 at Maryland: Comparing word-for-word gloss and MT

Jianqiang Wang
, Douglas W. Oard

Information Science

University of Maryland, College Park

Research output: Contribution to journal › Conference article › peer-review

Abstract

For the first interactive Cross-Language Evaluation Forum, the Maryland team focused on comparison of term-for-term gloss translation with full machine translation for the document selection task. The results show that (f) searchers are able to make relevance judgments with translations from either approach, and (2) the machine translation system achieved better effectiveness than the gloss translation strategy that we tried, although the difference is not statistically significant. It was noted that the "somewhat relevant" category was used differently by searchers presented with gloss translations than with machine translations, and some reasons for that difference are suggested. Finally, the results suggest that the F measure used in this evaluation is better suited for use with topics that have many known relevant documents than those with few.

Original language	English
Journal	CEUR Workshop Proceedings
Volume	1167
State	Published - 2001
Event	2001 Cross Language Evaluation Forum Workshop, CLEF 2001, co-located with the 5th European Conference on Digital Libraries, ECDL 2001 - Darmstad, Germany Duration: Sep 3 2001 → Sep 4 2001

Cite this

@article{ec78cab55f194e53be7f0f9905748bab,

title = "ICLEF 2001 at Maryland: Comparing word-for-word gloss and MT",

abstract = "For the first interactive Cross-Language Evaluation Forum, the Maryland team focused on comparison of term-for-term gloss translation with full machine translation for the document selection task. The results show that (f) searchers are able to make relevance judgments with translations from either approach, and (2) the machine translation system achieved better effectiveness than the gloss translation strategy that we tried, although the difference is not statistically significant. It was noted that the {"}somewhat relevant{"} category was used differently by searchers presented with gloss translations than with machine translations, and some reasons for that difference are suggested. Finally, the results suggest that the F measure used in this evaluation is better suited for use with topics that have many known relevant documents than those with few.",

author = "Jianqiang Wang and Oard, \{Douglas W.\}",

note = "Publisher Copyright: Copyright {\textcopyright} 2001 for the individual papers by the papers' authors.; 2001 Cross Language Evaluation Forum Workshop, CLEF 2001, co-located with the 5th European Conference on Digital Libraries, ECDL 2001 ; Conference date: 03-09-2001 Through 04-09-2001",

year = "2001",

language = "English",

volume = "1167",

journal = "CEUR Workshop Proceedings",

issn = "1613-0073",

publisher = "CEUR-WS",

}

TY - JOUR

T1 - ICLEF 2001 at Maryland

T2 - 2001 Cross Language Evaluation Forum Workshop, CLEF 2001, co-located with the 5th European Conference on Digital Libraries, ECDL 2001

AU - Wang, Jianqiang

AU - Oard, Douglas W.

PY - 2001

Y1 - 2001

N2 - For the first interactive Cross-Language Evaluation Forum, the Maryland team focused on comparison of term-for-term gloss translation with full machine translation for the document selection task. The results show that (f) searchers are able to make relevance judgments with translations from either approach, and (2) the machine translation system achieved better effectiveness than the gloss translation strategy that we tried, although the difference is not statistically significant. It was noted that the "somewhat relevant" category was used differently by searchers presented with gloss translations than with machine translations, and some reasons for that difference are suggested. Finally, the results suggest that the F measure used in this evaluation is better suited for use with topics that have many known relevant documents than those with few.

AB - For the first interactive Cross-Language Evaluation Forum, the Maryland team focused on comparison of term-for-term gloss translation with full machine translation for the document selection task. The results show that (f) searchers are able to make relevance judgments with translations from either approach, and (2) the machine translation system achieved better effectiveness than the gloss translation strategy that we tried, although the difference is not statistically significant. It was noted that the "somewhat relevant" category was used differently by searchers presented with gloss translations than with machine translations, and some reasons for that difference are suggested. Finally, the results suggest that the F measure used in this evaluation is better suited for use with topics that have many known relevant documents than those with few.

UR - https://www.scopus.com/pages/publications/84921988591

M3 - Conference article

AN - SCOPUS:84921988591

SN - 1613-0073

VL - 1167

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

Y2 - 3 September 2001 through 4 September 2001

ER -

ICLEF 2001 at Maryland: Comparing word-for-word gloss and MT

Abstract

Other files and links

Fingerprint

Cite this