{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,5,16]],"date-time":"2023-05-16T04:40:50Z","timestamp":1684212050079},"reference-count":22,"publisher":"Association for Computing Machinery (ACM)","issue":"3","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Transactions on Asian Language Information Processing"],"published-print":{"date-parts":[[2006,9]]},"abstract":"<jats:p>\n            This article presents an empirical study of four techniques for adapting language models, including a maximum\n            <jats:italic>a posteriori<\/jats:italic>\n            (MAP) method and three discriminative training models, in the application of Japanese\n            <jats:italic>Kana-Kanji<\/jats:italic>\n            conversion. We compare the performance of these methods from various angles by adapting the baseline model to four adaptation domains. In particular, we attempt to interpret the results in terms of the character error rate (CER) by correlating them with the characteristics of the adaptation domain, measured by using the information-theoretic notion of cross entropy. We show that such a metric correlates well with the CER performance of the adaptation methods, and also show that the discriminative methods are not only superior to a MAP-based method in achieving larger CER reduction, but also in having fewer side effects and being more robust against the similarity between background and adaptation domains.\n          <\/jats:p>","DOI":"10.1145\/1194936.1194939","type":"journal-article","created":{"date-parts":[[2007,1,16]],"date-time":"2007-01-16T19:38:29Z","timestamp":1168976309000},"page":"209-227","update-policy":"http:\/\/dx.doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["An empirical study on language model adaptation"],"prefix":"10.1145","volume":"5","author":[{"given":"Jianfeng","family":"Gao","sequence":"first","affiliation":[{"name":"Suzuki Microsoft Research, Redmond, WA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hisami","family":"Suzuki","sequence":"additional","affiliation":[{"name":"Suzuki Microsoft Research, Redmond, WA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Yuan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2006,9]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"International Conference on Acoustics, Speech, and Signal Processing (ICASSP)","author":"Bacchiani M.","year":"2003","unstructured":"Bacchiani , M. and Roark , B . 2003. Unsupervised language model adaptation . In International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2003 , 224--227. Bacchiani, M. and Roark, B. 2003. Unsupervised language model adaptation. In International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2003, 224--227."},{"key":"e_1_2_1_2_1","volume-title":"Human Language Technology Conference-North American Chapter of the Association for Computational Linguistics Aannual Meeting (HLT-NAACL). 21--24","author":"Bacchiani M.","unstructured":"Bacchiani , M. , Roark , B. , and Sara\u00e7lar , M . 2004. Language model adaptation with MAP estimation and the perceptron algorithm . In Human Language Technology Conference-North American Chapter of the Association for Computational Linguistics Aannual Meeting (HLT-NAACL). 21--24 . Bacchiani, M., Roark, B., and Sara\u00e7lar, M. 2004. Language model adaptation with MAP estimation and the perceptron algorithm. In Human Language Technology Conference-North American Chapter of the Association for Computational Linguistics Aannual Meeting (HLT-NAACL). 21--24."},{"key":"e_1_2_1_3_1","volume-title":"Proceedings of the ISCA Tutorial and Research Workshop (ITRW) on Adaptation Methods for Speech Recognition. 165--174","author":"Bellagarda J.","year":"2001","unstructured":"Bellagarda , J. 2001 . An overview of statistical language model adaptation . In Proceedings of the ISCA Tutorial and Research Workshop (ITRW) on Adaptation Methods for Speech Recognition. 165--174 . Bellagarda, J. 2001. An overview of statistical language model adaptation. In Proceedings of the ISCA Tutorial and Research Workshop (ITRW) on Adaptation Methods for Speech Recognition. 165--174."},{"key":"e_1_2_1_4_1","volume-title":"Proceedings of the International Conference on Machine Learning (ICML). 175--182","author":"Collins M.","year":"2000","unstructured":"Collins , M. 2000 . Discriminative reranking for natural language parsing . In Proceedings of the International Conference on Machine Learning (ICML). 175--182 . Collins, M. 2000. Discriminative reranking for natural language parsing. In Proceedings of the International Conference on Machine Learning (ICML). 175--182."},{"key":"e_1_2_1_5_1","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP). 1--8. 10","author":"Collins M.","year":"2002","unstructured":"Collins , M. 2002 . Discriminative training methods for hidden Markov models: Theory and experiments with perceptron algorithms . In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP). 1--8. 10 .3115\/1118693.1118694 Collins, M. 2002. Discriminative training methods for hidden Markov models: Theory and experiments with perceptron algorithms. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP). 1--8. 10.3115\/1118693.1118694"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007537716579"},{"key":"e_1_2_1_7_1","unstructured":"Duda R. O. Hart P. E. and Stork D. G. 2001. Pattern Classification. Wiley New York.   Duda R. O. Hart P. E. and Stork D. G. 2001. Pattern Classification. Wiley New York."},{"key":"e_1_2_1_8_1","volume-title":"Proceedings of the International Conference on Machine Learning (ICML). 170--178","author":"Freund Y","unstructured":"Freund , Y , Iyer , R. , Schapire , R. E. , and Singer , Y . 1998. An efficient boosting algorithm for combining preferences . In Proceedings of the International Conference on Machine Learning (ICML). 170--178 . Freund, Y, Iyer, R., Schapire, R. E., and Singer, Y. 1998. An efficient boosting algorithm for combining preferences. In Proceedings of the International Conference on Machine Learning (ICML). 170--178."},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/595576.595578"},{"key":"e_1_2_1_10_1","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP). 248--256","author":"Gao J.","year":"1869","unstructured":"Gao , J. , Suzuki , H. , and Wen , Y . 2002b. Using headword dependency and predictive clustering for language modeling . In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP). 248--256 . 10.3115\/11 1869 3.1118725 Gao, J., Suzuki, H., and Wen, Y. 2002b. Using headword dependency and predictive clustering for language modeling. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP). 248--256. 10.3115\/1118693.1118725"},{"key":"e_1_2_1_11_1","volume-title":"Proceedings of the Human Language Conference on Empirical Methods in Natural Language Processing (HLT-EMNLP). 209--216","author":"Gao J.","year":"2057","unstructured":"Gao . J. , Yu , H. , Yuan , W. , and Xu , P . 2005. Minimum sample risk methods for language modeling . In Proceedings of the Human Language Conference on Empirical Methods in Natural Language Processing (HLT-EMNLP). 209--216 . 10.3115\/12 2057 5.1220602 Gao. J., Yu, H., Yuan, W., and Xu, P. 2005. Minimum sample risk methods for language modeling. In Proceedings of the Human Language Conference on Empirical Methods in Natural Language Processing (HLT-EMNLP). 209--216. 10.3115\/1220575.1220602"},{"key":"e_1_2_1_12_1","volume-title":"Proceedings of the IEEE Conference on Acoustics, Speech and Signal Processing. IEEE","author":"Gillick L.","unstructured":"Gillick , L. and Cox , J . 1989. Some statistical issues in the comparison of speech recognition algorithms . In Proceedings of the IEEE Conference on Acoustics, Speech and Signal Processing. IEEE , New York, 532--535. Gillick, L. and Cox, J. 1989. Some statistical issues in the comparison of speech recognition algorithms. In Proceedings of the IEEE Conference on Acoustics, Speech and Signal Processing. IEEE, New York, 532--535."},{"key":"e_1_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Hastie T. Tibshirani R. and Friedman J. 2001. The Elements of Statistical Learning. Springer Verlag New York.  Hastie T. Tibshirani R. and Friedman J. 2001. The Elements of Statistical Learning. Springer Verlag New York.","DOI":"10.1007\/978-0-387-21606-5"},{"key":"e_1_2_1_14_1","volume-title":"Proceedings of the Association for Computational Linguistics Annual Meeting (ACL). 25--32","author":"Lee L.","year":"1999","unstructured":"Lee , L. 1999 . Measures of distributional similarity . In Proceedings of the Association for Computational Linguistics Annual Meeting (ACL). 25--32 . 10.3115\/1034678.1034693 Lee, L. 1999. Measures of distributional similarity. In Proceedings of the Association for Computational Linguistics Annual Meeting (ACL). 25--32. 10.3115\/1034678.1034693"},{"key":"e_1_2_1_15_1","unstructured":"Manning C.D. and Sch\u00fctze H. 1999. Foundations of Statistical Natural Language Processing. The MIT Press Cambridge MA.   Manning C.D. and Sch\u00fctze H. 1999. Foundations of Statistical Natural Language Processing. The MIT Press Cambridge MA."},{"key":"e_1_2_1_16_1","volume-title":"Machine Learning","author":"Mitchell T. M.","unstructured":"Mitchell , T. M. 1997. Machine Learning . McGraw-Hill , New York . Mitchell, T. M. 1997. Machine Learning. McGraw-Hill, New York."},{"key":"e_1_2_1_17_1","volume-title":"Proceedings of the Association for Computational Linguistics Annual Meeting (ACL). 160--167","author":"Och F.J.","year":"2003","unstructured":"Och , F.J. 2003 . Minimum error rate training in statistical machine translation . In Proceedings of the Association for Computational Linguistics Annual Meeting (ACL). 160--167 . 10.3115\/1075096.1075117 Och, F.J. 2003. Minimum error rate training in statistical machine translation. In Proceedings of the Association for Computational Linguistics Annual Meeting (ACL). 160--167. 10.3115\/1075096.1075117"},{"key":"e_1_2_1_18_1","volume-title":"C: The Art of Scientific Computing","author":"Press W. H.","year":"1992","unstructured":"Press , W. H. , Teukolsky , S. A. , Vetterling , W. T. , and Flannery , B. P . 1992 . Numerical Recipes in C: The Art of Scientific Computing . Cambridge University Press , New York . Press, W. H., Teukolsky, S. A., Vetterling, W. T., and Flannery, B. P. 1992. Numerical Recipes in C: The Art of Scientific Computing. Cambridge University Press, New York."},{"key":"e_1_2_1_19_1","volume-title":"Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP). 749--752","author":"Roark B.","unstructured":"Roark , B. , Saraclar , M. , and Collins , M . 2004. Corrective language modeling for large vocabulary ASR with the perceptron algorithm . In Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP). 749--752 . Roark, B., Saraclar, M., and Collins, M. 2004. Corrective language modeling for large vocabulary ASR with the perceptron algorithm. In Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP). 749--752."},{"key":"e_1_2_1_20_1","volume-title":"Proceedings of the Human Language Technology Conference-Conference on Empirical Methods in Natural Language Processing (HLT\/EMNLP). 265--272","author":"Suzuki H.","year":"2057","unstructured":"Suzuki , H. and Gao , J . 2005a. A comparative study on language model adaptation techniques using new evaluation metrics . In Proceedings of the Human Language Technology Conference-Conference on Empirical Methods in Natural Language Processing (HLT\/EMNLP). 265--272 . 10.3115\/12 2057 5.1220609 Suzuki, H. and Gao, J. 2005a. A comparative study on language model adaptation techniques using new evaluation metrics. In Proceedings of the Human Language Technology Conference-Conference on Empirical Methods in Natural Language Processing (HLT\/EMNLP). 265--272. 10.3115\/1220575.1220609"},{"key":"e_1_2_1_21_1","unstructured":"Suzuki H. and Gao J. 2005b. Microsoft research IME corpus. Microsoft Research Tech. Rep. TR-2005-168.  Suzuki H. and Gao J. 2005b. Microsoft research IME corpus. Microsoft Research Tech. Rep. TR-2005-168."},{"key":"e_1_2_1_22_1","unstructured":"Theodoridis S. and Koutroumbas K. 2003. Pattern Recognition. Elsevier New York.   Theodoridis S. and Koutroumbas K. 2003. Pattern Recognition. Elsevier New York."}],"container-title":["ACM Transactions on Asian Language Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1194936.1194939","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,28]],"date-time":"2022-12-28T21:42:10Z","timestamp":1672263730000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1194936.1194939"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006,9]]},"references-count":22,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2006,9]]}},"alternative-id":["10.1145\/1194936.1194939"],"URL":"https:\/\/doi.org\/10.1145\/1194936.1194939","relation":{},"ISSN":["1530-0226","1558-3430"],"issn-type":[{"value":"1530-0226","type":"print"},{"value":"1558-3430","type":"electronic"}],"subject":[],"published":{"date-parts":[[2006,9]]},"assertion":[{"value":"2006-09-01","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}