2024-03-28T21:24:13Zhttps://eprints.lib.hokudai.ac.jp/dspace-oai/requestoai:eprints.lib.hokudai.ac.jp:2115/641322022-11-17T02:08:08Zhdl_2115_20053hdl_2115_145Automatic Evaluation Method for Machine Translation using Noun-Phrase ChunkingHiroshi, Echizen-yaKenji, Araki007As described in this paper, we proposea new automatic evaluation method formachine translation using noun-phrasechunking. Our method correctly determinesthe matching words between twosentences using corresponding nounphrases. Moreover, our method determinesthe similarity between two sentencesin terms of the noun-phrase orderof appearance. Evaluation experimentswere conducted to calculate thecorrelation among human judgments,along with the scores produced usingautomatic evaluation methods forMT outputs obtained from the 12 machinetranslation systems in NTCIR-7. Experimental results show thatour method obtained the highest correlationsamong the methods in bothsentence-level adequacy and fluency.ACMConference Paperapplication/pdfhttp://hdl.handle.net/2115/64132https://eprints.lib.hokudai.ac.jp/dspace/bitstream/2115/64132/1/Automatic%20Evaluation%20Method%20for%20Machine%20Translation%20using%20Noun-Phrase%20Chunking.pdfProceedings of the 48th Annual Meeting of the Association for Computational Linguistics1081172010eng© 2010 ACM. This is the author’s version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, Pages 108-117 ,2010-07 ,http://doi.acm.org/10.1145/1860000.1858693author