{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T06:10:29Z","timestamp":1774159829463,"version":"3.50.1"},"reference-count":64,"publisher":"MIT Press - Journals","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computational Linguistics"],"published-print":{"date-parts":[[2013,12]]},"abstract":"<jats:p> In this article we investigate statistical machine translation (SMT) into Germanic languages, with a focus on compound processing. Our main goal is to enable the generation of novel compounds that have not been seen in the training data. We adopt a split-merge strategy, where compounds are split before training the SMT system, and merged after the translation step. This approach reduces sparsity in the training data, but runs the risk of placing translations of compound parts in non-consecutive positions. It also requires a postprocessing step of compound merging, where compounds are reconstructed in the translation output. We present a method for increasing the chances that components that should be merged are translated into contiguous positions and in the right order and show that it can lead to improvements both by direct inspection and in terms of standard translation evaluation metrics. We also propose several new methods for compound merging, based on heuristics and machine learning, which outperform previously suggested algorithms. These methods can produce novel compounds and a translation with at least the same overall quality as the baseline. For all subtasks we show that it is useful to include part-of-speech based information in the translation process, in order to handle compounds. <\/jats:p>","DOI":"10.1162\/coli_a_00162","type":"journal-article","created":{"date-parts":[[2013,4,23]],"date-time":"2013-04-23T15:04:50Z","timestamp":1366729490000},"page":"1067-1108","source":"Crossref","is-referenced-by-count":7,"title":["Generation of Compound Words in Statistical Machine Translation into Compounding Languages"],"prefix":"10.1162","volume":"39","author":[{"given":"Sara","family":"Stymne","sequence":"first","affiliation":[{"name":"Uppsala University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicola","family":"Cancedda","sequence":"additional","affiliation":[{"name":"Xerox Research Centre Europe"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lars","family":"Ahrenberg","sequence":"additional","affiliation":[{"name":"Link\u00f6ping University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"281","reference":[{"key":"R1","doi-asserted-by":"publisher","DOI":"10.3115\/1557690.1557732"},{"key":"R2","first-page":"65","volume-title":"Proceedings of the Workshop on Intrinsic and Extrinsic Evaluation Measures for MT and\/or Summarization at ACL'05","author":"Banerjee Satanjeev","year":"2005"},{"key":"R3","first-page":"470","volume-title":"Proceedings of the 15th European Conference on Artificial Intelligence (ECAI)","author":"Baroni Marco","year":"2002"},{"key":"R4","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.607814"},{"key":"R5","doi-asserted-by":"publisher","DOI":"10.3115\/1613715.1613809"},{"key":"R6","first-page":"341","volume-title":"Proceedings of the 24th International Conference on Computational Linguistics","author":"Botha Jan A.","year":"2012"},{"key":"R7","volume-title":"PILUS nr 38.","author":"Brodda Benny","year":"1979"},{"key":"R8","first-page":"12","volume-title":"Proceedings of the 9th International Conference of Theoretical and Methodological Issues in Machine Translation","author":"Brown Ralf D.","year":"2002"},{"key":"R9","unstructured":"Carlberger, Johan, Rickard Domeij, Viggo Kann, and Ola Knutsson. 2005. The development and performance of a grammar checker for Swedish: A language engineering perspective.In Ola Knutsson, editor, Developing and Evaluating Language Tools for Writers and Learners of Swedish. Ph.D. thesis, Royal Institute of Technology (KTH), Stockholm, Sweden."},{"key":"R10","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-024X(19990725)29:9<815::AID-SPE256>3.0.CO;2-F"},{"key":"R11","first-page":"72","volume-title":"Proceedings of the 46th Annual Meeting of the ACL: Human Language Technologies","author":"Cherry Colin","year":"2008"},{"key":"R12","first-page":"176","volume-title":"Proceedings of the 49th Annual Meeting of the ACL: Human Language Technologies","author":"Clark Jonathan H.","year":"2011"},{"key":"R13","doi-asserted-by":"publisher","DOI":"10.3115\/1118693.1118694"},{"key":"R14","doi-asserted-by":"publisher","DOI":"10.1162\/0891201053630273"},{"key":"R15","doi-asserted-by":"publisher","DOI":"10.3115\/974499.974523"},{"key":"R16","doi-asserted-by":"publisher","DOI":"10.3115\/1289189.1289273"},{"key":"R17","doi-asserted-by":"publisher","DOI":"10.3115\/1620754.1620814"},{"key":"R18","unstructured":"Dyer, Chris. 2010. A Formal Model of Ambiguity and its Applications in Machine Translation. Ph.D. thesis, University of Maryland, USA."},{"key":"R19","doi-asserted-by":"publisher","DOI":"10.3115\/1654650.1654653"},{"key":"R20","first-page":"45","volume-title":"LREC 2010 Workshop on Language Resources and Human Language Technology for Semitic Languages","author":"El Kholy Ahmed","year":"2010"},{"key":"R21","doi-asserted-by":"publisher","DOI":"10.3115\/1626431.1626455"},{"key":"R22","first-page":"224","volume-title":"Proceedings of the 16th Nordic Conference on Computational Linguistics (NODALIDA'07)","author":"Friberg Karin","year":"2007"},{"key":"R23","first-page":"224","volume-title":"Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR","author":"Fritzinger Fabienne","year":"2010"},{"issue":"2","key":"R24","volume":"7","author":"Hedlund Turid","year":"2002","journal-title":"Information Research"},{"key":"R25","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626378"},{"key":"R26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-78135-6_11"},{"key":"R28","first-page":"79","volume-title":"Proceedings of MT Summit X","author":"Koehn Philipp","year":"2005"},{"key":"R29","doi-asserted-by":"publisher","DOI":"10.3115\/1626394.1626412"},{"key":"R30","first-page":"868","volume-title":"Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning","author":"Koehn Philipp","year":"2007"},{"key":"R31","doi-asserted-by":"publisher","DOI":"10.3115\/1557769.1557821"},{"key":"R32","doi-asserted-by":"publisher","DOI":"10.3115\/1067807.1067833"},{"key":"R33","unstructured":"Kokkinakis, Dimitros. 2001. A Framework for the Acquisition of Lexical Knowledge: Description and Applications. Ph.D. thesis, G\u00f6teborg University, Sweden."},{"key":"R34","unstructured":"K\u00fcrschner, Sebastian. 2003. Von Volk-s-musik und Sport-\u00f8-geist im Lemming-\u00f8-land \u2013 Af folk-e-musik og sport-s-\u00e5nd i lemming-e-landet: Fugenelemente im Deutschen und D\u00e4nischen \u2013 eine kontrastive Studie zu einem Grenzfall der Morphologie.Master's thesis, Albert-Ludwigs-Universit\u00e4t, Freiburg, Germany."},{"key":"R35","first-page":"282","volume-title":"Proceedings of the 18th International Conference on Machine Learning","author":"Lafferty John","year":"2001"},{"key":"R36","first-page":"83","volume-title":"Tagungsband der 4. Konferenz zur Verarbeitung nat\u00fcrlicher Sprache (KONVENS)","author":"Langer Stefan","year":"1998"},{"key":"R37","first-page":"945","volume-title":"Proceedings of the Sixth International Conference on Spoken Language Processing","volume":"3","author":"Larson Martha","year":"2000"},{"key":"R38","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"},{"key":"R39","first-page":"1,395","volume-title":"Proceedings of the 49th Annual Meeting of the ACL: Human Language Technologies","author":"Macherey Klaus","year":"2011"},{"key":"R40","doi-asserted-by":"publisher","DOI":"10.3115\/992730.992809"},{"key":"R41","doi-asserted-by":"publisher","DOI":"10.1162\/089120104323093285"},{"key":"R42","doi-asserted-by":"publisher","DOI":"10.3115\/1075096.1075117"},{"key":"R43","doi-asserted-by":"publisher","DOI":"10.1162\/089120103321337421"},{"key":"R44","first-page":"311","volume-title":"Proceedings of the 40th Annual Meeting of the ACL","author":"Papineni Kishore","year":"2002"},{"key":"R45","first-page":"25","volume-title":"5th LREC SALTMIL Workshop on Minority Languages","author":"Popovi\u0107 Maja","year":"2006"},{"key":"R46","doi-asserted-by":"publisher","DOI":"10.1007\/11816508_61"},{"key":"R47","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"R48","first-page":"57","volume-title":"Proceedings of the Workshop on Intrinsic and Extrinsic Evaluation Measures for MT and\/or Summarization at ACL'05","author":"Riezler Stefan","year":"2005"},{"key":"R49","first-page":"1,185","volume-title":"Advances in Neural Information Processing Systems 17 (NIPS)","author":"Sarawagi Sunita","year":"2004"},{"key":"R50","first-page":"239","volume-title":"Proceedings of the Finite State Methods and Natural Language Processing","author":"Schiller Anne","year":"2005"},{"key":"R51","first-page":"44","volume-title":"Proceedings of the International Conference on New Methods in Language Processing","author":"Schmid Helmut","year":"1994"},{"key":"R52","doi-asserted-by":"publisher","DOI":"10.3115\/1599081.1599179"},{"key":"R53","doi-asserted-by":"publisher","DOI":"10.3115\/1220575.1220670"},{"key":"R54","first-page":"899","volume-title":"Proceedings of the 4th International Conference on Language Resources and Evaluation (LREC'04)","author":"Sj\u00f6bergh Jonas","year":"2004"},{"key":"R55","first-page":"901","volume-title":"Proceedings of the Seventh International Conference on Spoken Language Processing","author":"Stolcke Andreas","year":"2002"},{"key":"R56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-85287-2_44"},{"key":"R57","doi-asserted-by":"publisher","DOI":"10.3115\/1609179.1609187"},{"key":"R58","first-page":"250","volume-title":"Proceedings of the Sixth Workshop on Statistical Machine Translation","author":"Stymne Sara","year":"2011"},{"key":"R59","first-page":"180","volume-title":"Proceedings of the 12th Annual Conference of the European Association for Machine Translation","author":"Stymne Sara","year":"2008"},{"key":"R60","doi-asserted-by":"publisher","DOI":"10.3115\/1626394.1626411"},{"key":"R61","doi-asserted-by":"publisher","DOI":"10.3115\/974557.974568"},{"key":"R62","first-page":"25","volume-title":"Advances in Neural Information Processing Systems 16 (NIPS)","author":"Taskar Ben","year":"2003"},{"key":"R63","volume-title":"Svensk ordbildningsl\u00e4ra.","author":"Thorell Olof","year":"1981"},{"key":"R64","first-page":"1,453","volume":"6","author":"Tsochantaridis Ioannis","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"R65","first-page":"491","volume-title":"Proceedings of MT Summit XI","author":"Virpioja Sami","year":"2007"}],"container-title":["Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/COLI_a_00162","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T21:27:28Z","timestamp":1615584448000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/coli\/article\/39\/4\/1067-1108\/1447"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,12]]},"references-count":64,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2013,12]]}},"alternative-id":["10.1162\/COLI_a_00162"],"URL":"https:\/\/doi.org\/10.1162\/coli_a_00162","relation":{},"ISSN":["0891-2017","1530-9312"],"issn-type":[{"value":"0891-2017","type":"print"},{"value":"1530-9312","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,12]]}}}