%0 Conference Paper %1 Kaji:Kitsuregawa:11 %A Kaji, Nobuhiro %A Kitsuregawa, Masaru %B Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing (EMNLP-11) %C Edinburgh, UK %D 2011 %K 2011 compounds japanese splitting %T Splitting Noun Compounds via Monolingual and Bilingual Paraphrasing: A Study on Japanese Katakana Words %U http://aclweb.org/anthology-new/D/D11/D11-1089.pdf %X Word boundaries within noun compounds are not marked by white spaces in a number of languages, unlike in English, and it is beneficial for various NLP applications to split such noun compounds. In the case of Japanese, noun compounds made up of katakana words (i.e., transliterated foreign words) are particularly difficult to split, because katakana words are highly productive and are often out-of-vocabulary. To overcome this difficulty, we propose using monolingual and bilingual paraphrases of katakana noun compounds for identifying word boundaries. Experiments demonstrated that splitting accuracy is substantially improved by extracting such paraphrases from unlabeled textual data, the Web in our case, and then using that information for constructing splitting models.

@inproceedings{Kaji:Kitsuregawa:11, abstract = {Word boundaries within noun compounds are not marked by white spaces in a number of languages, unlike in English, and it is beneficial for various NLP applications to split such noun compounds. In the case of Japanese, noun compounds made up of katakana words (i.e., transliterated foreign words) are particularly difficult to split, because katakana words are highly productive and are often out-of-vocabulary. To overcome this difficulty, we propose using monolingual and bilingual paraphrases of katakana noun compounds for identifying word boundaries. Experiments demonstrated that splitting accuracy is substantially improved by extracting such paraphrases from unlabeled textual data, the Web in our case, and then using that information for constructing splitting models.}, added-at = {2011-09-13T11:36:14.000+0200}, address = {Edinburgh, UK}, author = {Kaji, Nobuhiro and Kitsuregawa, Masaru}, biburl = {https://www.bibsonomy.org/bibtex/298eb32ac8cbdfed15e356ec39c543293/seandalai}, booktitle = {Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing (EMNLP-11)}, interhash = {c872cbebbb63710fc4273076d6d179a4}, intrahash = {98eb32ac8cbdfed15e356ec39c543293}, keywords = {2011 compounds japanese splitting}, timestamp = {2011-09-13T11:36:14.000+0200}, title = {Splitting Noun Compounds via Monolingual and Bilingual Paraphrasing: A Study on Japanese Katakana Words}, url = {http://aclweb.org/anthology-new/D/D11/D11-1089.pdf}, year = 2011 }