{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,6,21]],"date-time":"2024-06-21T20:56:15Z","timestamp":1719003375190},"reference-count":19,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2010,3,1]],"date-time":"2010-03-01T00:00:00Z","timestamp":1267401600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Machine Translation"],"published-print":{"date-parts":[[2010,3]]},"DOI":"10.1007\/s10590-010-9073-6","type":"journal-article","created":{"date-parts":[[2010,4,19]],"date-time":"2010-04-19T11:11:19Z","timestamp":1271675479000},"page":"51-65","source":"Crossref","is-referenced-by-count":7,"title":["Significance tests of automatic machine translation evaluation metrics"],"prefix":"10.1007","volume":"24","author":[{"given":"Ying","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stephan","family":"Vogel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2010,4,20]]},"reference":[{"key":"9073_CR1","doi-asserted-by":"crossref","unstructured":"Amig\u00f3 E, Gonzalo J, Pe\u00f1as A, Verdejo F (2005) QARLA: a framework for the evaluation of text summarization systems. In: ACL \u201905: Proceedings of the 43rd annual meeting on association for computational linguistics. Association for Computational Linguistics, Morristown, NJ, USA, pp 280\u2013289","DOI":"10.3115\/1219840.1219875"},{"key":"9073_CR2","doi-asserted-by":"crossref","unstructured":"Amig\u00f3 E, Gim\u00e9nez J, Gonzalo J, M\u00e0rquez L (2006) MT evaluation: human-like vs. human acceptable. In: Proceedings of the COLING\/ACL on main conference poster sessions. Association for Computational Linguistics, Morristown, NJ, USA, pp 17\u201324","DOI":"10.3115\/1273073.1273076"},{"key":"9073_CR3","unstructured":"Banerjee S, Lavie A (2005) METEOR: an automatic metric for MT evaluation with improved correlation with human judgments\u2019. In: Proceedings of the ACL workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. Association for Computational Linguistics, Ann Arbor, Michigan, pp 65\u201372"},{"key":"9073_CR4","doi-asserted-by":"crossref","unstructured":"Bisani M, Ney H (2004) Bootstrap estimates for confidence intervals in ASR performance evaluation. In: Proceedings of the 2004 IEEE international conference on acoustics, speech, and signal processing (ICASSP 2004). Montreal, Quebec, Canada","DOI":"10.1109\/ICASSP.2004.1326009"},{"key":"9073_CR5","unstructured":"Callison-Burch C, Osborne M, Koehn P (2006) Re-evaluation the role of bleu in machine translation research. In: Proceedings of the 11th conference of the European chapter of the association for computational linguistics: EACL 2006. Trento, Italy, pp 249\u2013256"},{"key":"9073_CR6","doi-asserted-by":"crossref","unstructured":"Callison-Burch C, Fordyce C, Koehn P, Monz C, Schroeder J (2007) (Meta-) evaluation of machine translation. In: StatMT \u201907: Proceedings of the second workshop on statistical machine translation. Association for Computational Linguistics, Morristown, NJ, USA, pp 136\u2013158","DOI":"10.3115\/1626355.1626373"},{"key":"9073_CR7","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4899-4541-9","volume-title":"An introduction to the bootstrap","author":"B Efron","year":"1993","unstructured":"Efron B, Tibshirani R (1993) An introduction to the bootstrap. Chapman & Hall, Boca Raton"},{"key":"9073_CR8","unstructured":"Koehn P (2004) Statistical significance tests for machine translation evaluation. In: Proceedings of EMNLP 2004. Barcelona, Spain"},{"key":"9073_CR9","unstructured":"Leusch G, Ueffing N, Ney H (2003) A novel string-to-string distance measurewith applications to machine translation evaluation. In: Proceedings of MT Summit IX. New Orleans, LA"},{"key":"9073_CR10","doi-asserted-by":"crossref","unstructured":"Lin C-Y, Och FJ (2004) ORANGE: a method for evaluating automatic evaluation metrics for machine translation. In: COLING \u201904: Proceedings of the 20th international conference on computational linguistics. Association for Computational Linguistics, Morristown, NJ, USA, p 501","DOI":"10.3115\/1220355.1220427"},{"key":"9073_CR11","unstructured":"Liu D, Gildea D (2005) Syntactic features for evaluation of machine translation. In: ACL 2005 workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization"},{"key":"9073_CR12","unstructured":"Nie\u00dfen S, Vogel S, Ney H, Tillmann C (1998) A DP based search algorithm for statistical machine translation. In: Proceedings of the 17th international conference on computational linguistics. Association for Computational Linguistics, Morristown, NJ, USA, pp 960\u2013967"},{"key":"9073_CR13","unstructured":"NIST (2003) Automatic evaluation of machine translation quality using N-gram co-occurrence statistics. Technical report, NIST, http:\/\/www.nist.gov\/speech\/tests\/mt\/doc\/ngram-study.pdf"},{"issue":"2","key":"9073_CR14","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1007\/s10590-008-9038-1","volume":"21","author":"K Owczarzak","year":"2007","unstructured":"Owczarzak K, Genabith J, Way A (2007) Evaluating machine translation with LFG dependencies. Mach Transl 21(2): 95\u2013119","journal-title":"Mach Transl"},{"key":"9073_CR15","doi-asserted-by":"crossref","unstructured":"Pado S, Galley M, Jurafsky D, Manning CD (2009) Robust machine translation evaluation with entailment features. In: Proceedings of the joint conference of the 47th annual meeting of the ACL and the 4th international joint conference on natural language processing of the AFNLP. Association for Computational Linguistics, Suntec, Singapore, pp 297\u2013305","DOI":"10.3115\/1687878.1687922"},{"key":"9073_CR16","doi-asserted-by":"crossref","unstructured":"Papineni K, Roukos S, Ward T, Zhu W (2001) Bleu: a method for automatic evaluation of machine translation. Technical Report RC22176(W0109-022), IBM Research Division, Thomas J. Watson Research Center","DOI":"10.3115\/1073083.1073135"},{"key":"9073_CR17","unstructured":"Snover M, Dorr B, Schwartz R, Micciulla L, Makhoul J (2006) A study of translation edit rate with targeted human annotation. In: Proceedings AMTA, pp 223\u2013231"},{"key":"9073_CR18","unstructured":"Zhang Y (2008) Structured language model for statistical machine translation. Ph.D. thesis, Carnegie Mellon University, Pittsburgh, PA"},{"key":"9073_CR19","unstructured":"Zhang Y, Vogel S, Waibel A (2004) Interpreting Bleu\/NIST scores: how much improvement do we need to have a better system? In: Proceedings of the 4th international conference on language resources and evaluation. Lisbon, Portugal"}],"container-title":["Machine Translation"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10590-010-9073-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10590-010-9073-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10590-010-9073-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,30]],"date-time":"2019-05-30T18:37:45Z","timestamp":1559241465000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10590-010-9073-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,3]]},"references-count":19,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2010,3]]}},"alternative-id":["9073"],"URL":"https:\/\/doi.org\/10.1007\/s10590-010-9073-6","relation":{},"ISSN":["0922-6567","1573-0573"],"issn-type":[{"value":"0922-6567","type":"print"},{"value":"1573-0573","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,3]]}}}