{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:11:20Z","timestamp":1742911880643,"version":"3.40.3"},"publisher-location":"Boston, MA","reference-count":66,"publisher":"Springer US","isbn-type":[{"type":"print","value":"9781461432227"},{"type":"electronic","value":"9781461432234"}],"license":[{"start":{"date-parts":[[2012,1,1]],"date-time":"2012-01-01T00:00:00Z","timestamp":1325376000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2012,1,1]],"date-time":"2012-01-01T00:00:00Z","timestamp":1325376000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-1-4614-3223-4_10","type":"book-chapter","created":{"date-parts":[[2012,2,2]],"date-time":"2012-02-02T16:49:22Z","timestamp":1328201362000},"page":"323-359","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Translingual Mining from Text Data"],"prefix":"10.1007","author":[{"given":"Jian-Yun","family":"Nie","sequence":"first","affiliation":[]},{"given":"Jianfeng","family":"Gao","sequence":"additional","affiliation":[]},{"given":"Guihong","family":"Cao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2012,1,7]]},"reference":[{"key":"10_CR1_En","unstructured":"Adafre, S.F. and de Rijke, M. (2006). Finding similar sentences acorss multiple languages in Wikipedia. 11 th Conference of the European Chapter of the Association for Computational Linguistics, pp. 62\u201369."},{"key":"10_CR2_En","doi-asserted-by":"crossref","unstructured":"Ballesteros, L. and Croft, W. (1997). Phrasal translation and query expansion techniques for cross-language information retrieval. In Proceedings of SIGIR Conf. pp. 84-91.","DOI":"10.1145\/278459.258540"},{"key":"10_CR3_En","doi-asserted-by":"crossref","unstructured":"Berger, A. and Lafferty, J. (1999). Information retrieval as statistical translation. In Proceedings of SIGIR Conf., pp. 222-229.","DOI":"10.1145\/312624.312681"},{"key":"10_CR4_En","doi-asserted-by":"crossref","unstructured":"Braschler, M., and Sch\u00e4uble, P. (1998). Multilingual information retrieval based on document alignment techniques. ECDL \u201998: Proceedings of the Second European Conference on Research and Advanced Technology for Digital Libraries, pp. 183\u2013197.","DOI":"10.1007\/3-540-49653-X_12"},{"key":"10_CR5_En","doi-asserted-by":"crossref","unstructured":"Braschler, M., and Sch\u00e4uble, P. (2001). Experiments with the Eurospider Retrieval System for CLEF 2000, in Proceedings of CLEF Conference. pp. 140-148.","DOI":"10.1007\/3-540-44645-1_13"},{"issue":"2","key":"10_CR6_En","first-page":"263","volume":"19","author":"P Brown","year":"1993","unstructured":"Brown, P., Della Pietra, S., Della Pietra, V., and Mercer, R. (1993). The mathematics of statistical machine translation: Parameter estimation. Computational Linguistics, 19(2), pp. 263-311.","journal-title":"Computational Linguistics"},{"key":"10_CR7_En","unstructured":"Cao, G., Gao, J., Nie, J.Y. (2007) A system to mine large-scale bilingual dictionaries from monolingual Web pages, MT Summit, pp. 57-64."},{"key":"10_CR8_En","unstructured":"Carbonell, J.G, Yang, Y, Frederking, R.E., Brown, R., Geng, Y. and Lee, D. (1997) Translingual information retrieval: A comparative evaluation. In: Proceedings of the International Joint Conference on Arti?cial Intelligence (IJCAI \u201997)."},{"key":"10_CR9_En","doi-asserted-by":"crossref","unstructured":"Chiang, D., (2005) A Hierarchical Phrase-Based Model for Statistical Machine Translation. ACL.","DOI":"10.3115\/1219840.1219873"},{"key":"10_CR10_En","doi-asserted-by":"crossref","unstructured":"Chen, J., Nie, J.Y., (2000) Automatic construction of parallel English-Chinese corpus for cross-language information retrieval. ANLP pp. 21-28","DOI":"10.3115\/974147.974151"},{"issue":"5","key":"10_CR11_En","doi-asserted-by":"publisher","first-page":"645","DOI":"10.1002\/asi.20327","volume":"57","author":"HH Chen","year":"2006","unstructured":"Chen, H.H., Lin, W.C. and Yang, C.H. (2006). Translation-Transliterating Named Entities for Multilingual Information Access. Journal of the American Society for Information Science and Technology, 57(5):645-659","journal-title":"Journal of the American Society for Information Science and Technology"},{"key":"10_CR12_En","doi-asserted-by":"crossref","unstructured":"Cheng, P., Teng, J., Chen, R., Wang, J., Lu, W., and Chien, L. (2004). Translating Unknown Queries with Web Corpora for Cross- Language Information Retrieval. In Proceedings of SIGIR Conf., pp.162-169.","DOI":"10.1145\/1008992.1009020"},{"key":"10_CR13_En","volume-title":"(1997) Automatic cross-language retrieval using Latent Semantic Indexing","author":"ST Dumais","year":"1997","unstructured":"Dumais, S. T., Letsche, T. A., Littman, M. L. and Landauer, T. K. (1997) Automatic cross-language retrieval using Latent Semantic Indexing. AAAI Spring Symposuim on Cross-Language Text and Speech Retrieval, March 1997."},{"key":"10_CR14_En","unstructured":"Franz, M., McCarley, J.S. and Koukos, S. (1999) Ad hoc and multilingual information retrieval at IBM. Proceedings of the Seventh Text Retrieval Conference (TREC-7), pp. 157\u2013168."},{"key":"10_CR15_En","doi-asserted-by":"crossref","unstructured":"Fung, P. (1995). A Pattern Matching Method for Finding Noun and Proper Noun Translations from Noisy Parallel Corpora. Proceedings of the Association for Computational Linguistics, pp. 236-243.","DOI":"10.3115\/981658.981690"},{"key":"10_CR16_En","doi-asserted-by":"crossref","unstructured":"Pascale Fung and Yuen Yee Lo. 1998. An IR approach for translating new words from nonparallel, comparable texts. Proceedings of COLING-ACL98, pp. 414\u2013 420.","DOI":"10.3115\/980451.980916"},{"key":"10_CR17_En","unstructured":"Fung, P. and McKeown, K. (1997) Finding terminology translations from non-parallel corpora. In: The 5th Annual Workshop on Very Large Corpora."},{"key":"10_CR18_En","doi-asserted-by":"crossref","unstructured":"Fung, P. and Cheung, P. (2004) Multilevel boot-strapping for extracting parallel sentences from a quasi parallel corpus. Conference on Empirical Methods in Natural Language Processing (EMNLP 04), pp. 1051\u20131057.","DOI":"10.3115\/1220355.1220506"},{"issue":"3","key":"10_CR19_En","first-page":"75","volume":"19","author":"WA Gale","year":"1993","unstructured":"Gale, W. A., Church K. W. 1993. A Program for Aligning Sentences in Bilingual Corpora. Computational Linguistics, 19(3): 75-102.","journal-title":"Computational Linguistics"},{"key":"10_CR20_En","doi-asserted-by":"crossref","unstructured":"Galley, M., Hopkins, M., Knight, K., Marcu, D., (2004) What\u2019s in a translation rule? HLT-NAACL, pp. 273-280","DOI":"10.21236\/ADA460212"},{"key":"10_CR21_En","first-page":"21","volume":"2010","author":"PG Otero","year":"2009","unstructured":"Pablo Gamallo Otero, Isaac Gonzalez Lopez, (2009) Wikipedia as Multilingual Source of Comparable Corpora, Proceedings of the 3rd Workshop on Building and Using Comparable Corpora, LREC 2010, pp. 21\u201325","journal-title":"LREC"},{"key":"10_CR22_En","doi-asserted-by":"crossref","unstructured":"Gao, J., Nie, J.Y., Xun, E., Zhang, J., Zhou, M., and Huang, C. (2001). Improving query translation for cross-language information retrieval using statistical models. In Proceedings of SIGIR Conf., pp. 96-104.","DOI":"10.1145\/383952.383966"},{"key":"10_CR23_En","doi-asserted-by":"crossref","unstructured":"Gao, J., Zhou, M., Nie, J.Y., He, H., Chen, W. (2002) Resolving query translation ambiguity using a decaying co-occurrence model and syntactic dependence relations. SIGIR, pp. 183-190","DOI":"10.1145\/564376.564409"},{"key":"10_CR24_En","first-page":"2006","volume":"194\u2013201","author":"J Gao","year":"2006","unstructured":"Gao, J., Nie, J.Y. (2006) Study of Statistical Models for Query Translation: Finding a Good Unit of Translation. SIGIR, pp 194- 201, 2006.","journal-title":"SIGIR, pp"},{"key":"10_CR25_En","first-page":"2010","volume":"1139\u20131148","author":"J Gao","year":"2010","unstructured":"Gao, J., He, X., Nie. J.Y. (2010) Clickthrough-based translation models for web search: from word models to phrase models. CIKM, pp 1139-1148, 2010.","journal-title":"CIKM, pp"},{"key":"10_CR26_En","unstructured":"Hong, Gumwon, Li, Chi-Ho, Zhou, Ming and Rim, Hae-Chang (2010) An Empirical Study on Web Mining of Parallel Data, COLING, pp. 474\u2013482."},{"key":"10_CR27_En","unstructured":"Huang, Degen, Zhao, Lian, Li, Lishuang Yu, Haitao (2010) Mining Large-scale Comparable Corpora from Chinese-English News Collections, COLING, pp. 472-480."},{"key":"10_CR28_En","doi-asserted-by":"crossref","unstructured":"Huang, F., Zhang, Y., and Vogel, S. (2005). Mining Key Phrase Translations from Web Corpora. In Proceedings of HLT-EMNLP Conf., pp. 483-490.","DOI":"10.3115\/1220575.1220636"},{"key":"10_CR29_En","doi-asserted-by":"crossref","unstructured":"Jeon, J. Lavrenko, V. and Manmatha, R. (2003) Automatic Image Annotation and Retrieval using Cross-Media Relevance Models, SIGIR, pp. 119-126.","DOI":"10.1145\/860435.860459"},{"issue":"4","key":"10_CR30_En","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1016\/S0306-4573(98)00055-7","volume":"35","author":"KS Jeong","year":"1999","unstructured":"Jeong, K.S., Myaeng, S.H., Lee, J.S, and Choi, K.S., (1999) Automatic identification and back-transliteration of foreign words for information retrieval, Information Processing and Management, 35(4), pp. 523-540.","journal-title":"Information Processing and Management"},{"key":"10_CR31_En","doi-asserted-by":"crossref","unstructured":"Ji, Heng (2009) Mining Name Translations from Comparable Corpora by Creating Bilingual Information Networks, Proceedings of the 2 nd Workshop on Building and Using Comparable Corpora, ACL-IJCNLP 2009, pages34\u201337.","DOI":"10.3115\/1690339.1690349"},{"key":"10_CR32_En","doi-asserted-by":"crossref","unstructured":"Koehn, P., Och, F.J., Marcus, D., (2003) Statistical phrase-based translation, In Proceedings of HLT-NAACL, pp. 48-54.","DOI":"10.21236\/ADA461156"},{"key":"10_CR33_En","doi-asserted-by":"crossref","unstructured":"Koehn, P. (2009) Statistical Machine Translation. Cambridge University Press.","DOI":"10.1017\/CBO9780511815829"},{"issue":"3","key":"10_CR34_En","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1162\/089120103322711587","volume":"29","author":"W. Kraaij","year":"2003","unstructured":"Kraaij, W., Nie, J.Y., and Simard, M. (2003). Embedding Web-Based Statistical Translation Models in Cross-Language Information Retrieval. Computational Linguistics, 29(3): 381-420.","journal-title":"Computational Linguistics"},{"key":"10_CR35_En","unstructured":"Kumano, T. and Tanaka, H., Tokunaga, T. (2007) Extracting phrasal alignments from comparable corpora by using joint probability SMT model. 11th International Conference on Theoretical and Methodological Issues in Machine Translation (TMI\u201907)."},{"key":"10_CR36_En","doi-asserted-by":"crossref","unstructured":"Kuo, J.S., Li, H., and Yang Y.K (2006). Learning Transliteration Lexicon from the Web. In the Proceedings of COLING\/ACL, pp.1129-1136","DOI":"10.3115\/1220175.1220317"},{"key":"10_CR37_En","doi-asserted-by":"crossref","unstructured":"Lam, W., Chan, S.K., and Huang, R. (2007). Named Entity Translation Matching and Learning: With Application for Mining Unseen Translations. ACM Transactions on Information Systems, 25(1), pp.","DOI":"10.1145\/1198296.1198298"},{"key":"10_CR38_En","doi-asserted-by":"crossref","unstructured":"Liu, Y., Jin R. and Chai, Joyce Y. (2005). A maximum coherence model for dictionary-based cross-language information retrieval, In Proceedings of SIGIR conf., pp. 536-543.","DOI":"10.1145\/1076034.1076125"},{"key":"10_CR39_En","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1145\/984321.984324","volume":"22","author":"W Lu","year":"2004","unstructured":"Lu, W. Chien, L.F. and Lee, H. (2004). Anchor Text Mining for Translation of Web Queries: A Transitive Translation Approach. ACM Transactions on Information Systems, Vol.22, pp. 242-269.","journal-title":"ACM Transactions on Information Systems"},{"key":"10_CR40_En","unstructured":"Ma, X. and Liberman, M., (1999). Bits: A Method for Bilingual Text Search over the Web. Proceedings of Machine Translation Summit VII."},{"key":"10_CR41_En","doi-asserted-by":"crossref","unstructured":"Munteanu, D. S., Marcu, D. (2005) Improving Machine Translation Performance by Exploiting Non-Parallel Corpora. 2005. Computational Linguistics. 31(4). pp: 477-504.","DOI":"10.1162\/089120105775299168"},{"key":"10_CR42_En","doi-asserted-by":"crossref","unstructured":"Munteanu, D. S. and Marcu D. (2006). Extracting parallel subsentential fragments from non-parallel corpora. ACL, pp. 81\u201388.","DOI":"10.3115\/1220175.1220186"},{"key":"10_CR43_En","doi-asserted-by":"crossref","unstructured":"Nagata, M., Saito, T., and Suzuki, K. (2001). Using the web as a bilingual dictionary. In Proceedings of the Workshop on Data-Driven Methods in Machine Translation (with ACL Conf.), pp. 1-8.","DOI":"10.3115\/1118037.1118050"},{"key":"10_CR44_En","unstructured":"Nie, J.Y., Cai, J. (2001) Filtering parallel corpora of web pages, IEEE symposium on NLP and Knowledge Engineering, pp. 453-458."},{"key":"10_CR45_En","doi-asserted-by":"crossref","unstructured":"Nie, J.Y., Simard, M., Isabelle, P., Durand, R. (1999) Cross-Language Information Retrieval based on Parallel Texts and Automatic Mining of Parallel Texts in the Web, In Proceedings of SIGIR Conf., pp. 74-81","DOI":"10.1145\/312624.312656"},{"key":"10_CR46_En","doi-asserted-by":"crossref","unstructured":"Och, F., and Ney, H. (2002) Discriminative Training and Maximum Entropy Models for Statistical Machine Translation. ACL, pp. 295-302","DOI":"10.3115\/1073083.1073133"},{"key":"10_CR47_En","doi-asserted-by":"crossref","unstructured":"Och, F. (2003). Minimum error rate training in statistical machine translation. In Proceedings of ACL. pp. 160-67","DOI":"10.3115\/1075096.1075117"},{"key":"10_CR48_En","first-page":"414","volume":"3687","author":"AI Oumohmed","year":"2005","unstructured":"Oumohmed, A.I., Mignotte, M., Nie, J.Y. (2005) Semantic-Based Cross-Media Image Retrieval, Pattern Recognition and Image Analysis: Third International Conference on Advances in Pattern Recognition (ICAPR), LNCS 3687, pp. 414-423.","journal-title":"LNCS"},{"key":"10_CR49_En","first-page":"522","volume":"4956","author":"M Potthast","year":"2008","unstructured":"Potthast, M., Stein, B., Anderka, M. (2008) A Wikipedia-based Multilingual Retrieval Model. ECIR, LNCS 4956, pp. 522\u2013530.","journal-title":"ECIR, LNCS"},{"key":"10_CR50_En","doi-asserted-by":"crossref","unstructured":"Qu, Y., Grefenstette, G., and Evans, D. A. (2003). Automatic transliteration for Japanese-to-English text retrieval. In Proceedings of SIGIR Conference, pp. 353-360.","DOI":"10.1145\/860435.860499"},{"key":"10_CR51_En","doi-asserted-by":"crossref","unstructured":"Rapp, R. (1995). Identifying Word Translations in Non-Parallel Texts. Proceedings of the 33rd Annual Meeting of the Association for Computational Linguistics, pp. 320-322.","DOI":"10.3115\/981658.981709"},{"key":"10_CR52_En","doi-asserted-by":"crossref","unstructured":"Resnik, P., (1999) Mining the Web for Bilingual Text, 37th Annual Meeting of the Association for Computational Linguistics (ACL\u201999).","DOI":"10.3115\/1034678.1034757"},{"key":"10_CR53_En","doi-asserted-by":"crossref","unstructured":"Resnik P. and Smith. N.A. (2003) The Web as a Parallel Corpus, Computational Linguistics, 29(3), pp. 349-380, September 2003.","DOI":"10.1162\/089120103322711578"},{"key":"10_CR54_En","doi-asserted-by":"crossref","unstructured":"Sheridan, P. and Ballerini, J. P. (1996). Experiments in multilingual information retrieval using the SPIDER system. In Proceedings of SIGIR Conf., pp. 58-65.","DOI":"10.1145\/243199.243213"},{"key":"10_CR55_En","unstructured":"Sch\u00f6nhofen, P., Bencz\u00far, A., B\u00edr\u00f3, I., Csalog\u00e1ny, K. (2007) Performing cross-language retrieval with Wikipedia, CLEF-2007 (http:\/\/www.clefcampaign.org\/2007\/working notes\/schonhofenCLEF2007.pdf)"},{"key":"10_CR56_En","doi-asserted-by":"crossref","unstructured":"Shi, L., Niu, C., Zhou, M., and Gao, J. (2006) A DOM Tree Alignment Model for Mining Parallel Data from the Web, ACL, pp. 489-496.","DOI":"10.3115\/1220175.1220237"},{"key":"10_CR57_En","unstructured":"Smith, J. R., Quirk, C., and Toutanova, K. (2010) Extracting parallel sentences from comparable corpora using document level alignment. HLT, pp. 403\u2013411"},{"key":"10_CR58_En","doi-asserted-by":"crossref","unstructured":"Sproat, R., Tao, T., Zhai, C. (2006) Named Entity Transliteration with Comparable Corpora. In Proceedings of ACL.","DOI":"10.3115\/1220175.1220185"},{"key":"10_CR59_En","doi-asserted-by":"crossref","unstructured":"Tuomas Talvensaari, Jorma Laurikkala, Kalervo J\u00e4rvelin, Martti Juhola (2006) A study on automatic creation of a comparable document collection in cross-language information retrieval, Journal of Documentation, Vol. 62 No. 3, pp. 372-387","DOI":"10.1108\/00220410610666510"},{"key":"10_CR60_En","doi-asserted-by":"crossref","unstructured":"Tuomas Talvensaari, Jorma Laurikkala, Kalervo J\u00e4rvelin, Martti Juhola, and Heikki Keskustalo (2007). Creating and exploiting a comparable corpus in cross-language information retrieval. ACM Trans. Inf. Syst. 25, 1, Article 4.","DOI":"10.1145\/1198296.1198300"},{"key":"10_CR61_En","doi-asserted-by":"crossref","unstructured":"Utiyama M. and Isahara, H. (2003) Reliable Measures for Aligning Japanese-English News Articles and Sentences. ACL, pp. 72\u201379.","DOI":"10.3115\/1075096.1075106"},{"key":"10_CR62_En","doi-asserted-by":"crossref","unstructured":"Jinxi Xu, W. Bruce Croft (1996) Query Expansion Using Local and Global Document Analysis. SIGIR, pp. 4-11","DOI":"10.1145\/243199.243202"},{"issue":"8","key":"10_CR63_En","doi-asserted-by":"publisher","first-page":"730","DOI":"10.1002\/asi.10261","volume":"54","author":"CC Yang","year":"2003","unstructured":"Yang, Christopher C., and Kar Wing Li. 2003. Automatic construction of English\/Chinese parallel corpora. Journal of the American Society for Information Science and Technology, 54(8), pp. 730\u2013742.","journal-title":"Journal of the American Society for Information Science and Technology"},{"key":"10_CR64_En","doi-asserted-by":"crossref","unstructured":"Zhang, Y. and Vines, P. (2004). Using the Web for Automated Translation Extraction in Cross-Language Information Retrieval. In Proceedings of SIGIR Conf., pp.162-169.","DOI":"10.1145\/1008992.1009022"},{"key":"10_CR65_En","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Huang, F., Vogel, S. (2005) Mining Translations of OOV Terms from the Web through Cross-lingual Query Expansion, SIGIR, pp. 669-670.","DOI":"10.1145\/1076034.1076182"},{"key":"10_CR66_En","unstructured":"Zhao, B., and Vogel, S. (2002). Adaptive Parallel Sentences Mining from Web Bilingual News Collection. In Proceedings of IEEE international conference on data mining, pages 745-750."}],"container-title":["Mining Text Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-1-4614-3223-4_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,18]],"date-time":"2023-02-18T23:38:18Z","timestamp":1676763498000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-1-4614-3223-4_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9781461432227","9781461432234"],"references-count":66,"URL":"https:\/\/doi.org\/10.1007\/978-1-4614-3223-4_10","relation":{},"subject":[],"published":{"date-parts":[[2012]]},"assertion":[{"value":"7 January 2012","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}