TY - GEN
T1 - Who, What, When, Where, Why? Comparing multiple approaches to the cross-lingual 5W task
AU - Parton, Kristen
AU - McKeown, Kathleen R.
AU - Coyne, Bob
AU - Diab, Mona T.
AU - Grishman, Ralph
AU - Hakkani-Tür, Dilek
AU - Harper, Mary
AU - Ji, Heng
AU - Ma, Weiyun
AU - Meyers, Adam
AU - Stolbach, Sara
AU - Sun, Ang
AU - Tur, Gokhan
AU - Xu, Wei
AU - Yaman, Sibel
PY - 2009
Y1 - 2009
N2 - Cross-lingual tasks are especially difficult due to the compounding effect of errors in language processing and errors in machine translation (MT). In this paper, we present an error analysis of a new cross-lingual task: the 5W task, a sentence-level understanding task which seeks to return the English 5W's (Who, What, When, Where and Why) corresponding to a Chinese sentence. We analyze systems that we developed, identifying specific problems in language processing and MT that cause errors. The best cross-lingual 5W system was still 19% worse than the best monolingual 5W system, which shows that MT significantly degrades sentence-level understanding. Neither source-language nor targetlanguage analysis was able to circumvent problems in MT, although each approach had advantages relative to the other. A detailed error analysis across multiple systems suggests directions for future research on the problem.
AB - Cross-lingual tasks are especially difficult due to the compounding effect of errors in language processing and errors in machine translation (MT). In this paper, we present an error analysis of a new cross-lingual task: the 5W task, a sentence-level understanding task which seeks to return the English 5W's (Who, What, When, Where and Why) corresponding to a Chinese sentence. We analyze systems that we developed, identifying specific problems in language processing and MT that cause errors. The best cross-lingual 5W system was still 19% worse than the best monolingual 5W system, which shows that MT significantly degrades sentence-level understanding. Neither source-language nor targetlanguage analysis was able to circumvent problems in MT, although each approach had advantages relative to the other. A detailed error analysis across multiple systems suggests directions for future research on the problem.
UR - http://www.scopus.com/inward/record.url?scp=80053388676&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=80053388676&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:80053388676
SN - 9781617382581
T3 - ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.
SP - 423
EP - 431
BT - ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.
T2 - Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language Processing of the AFNLP, ACL-IJCNLP 2009
Y2 - 2 August 2009 through 7 August 2009
ER -