Corpus-Based Machine Translation
Svenska sidor
Project overview
Publications
Members
Links
KOMA Publications
Ahrenberg, Lars, Magnus Merkel, Mikael Andersson: A System for Incremental and Interactive Word Linking. Third International Conference on Language Resources and Evaluation (LREC 2002), Las Palmas, 29-31 May 2002.
Ahrenberg, Lars, Magnus Merkel, Michael Petterstedt: Interactive Word Alignment for Language Engineering. Project note at The 10th Conference of the European Chapter of the Association for Computational Linguistics April 12-17, 2003 Agro Hotel, Budapest, Hungary (EACL-2003).
Ahrenberg, Lars och Maria Holmqvist, 2004. Back to the Future? The Case for English-Swedish Direct Machine Translation. Paper presented at the workshop on Recent Advances in Scandinavian Machine Translation (RASMAT 2004), Uppsala, 23. April, 2004.
Ahrenberg, Lars. Codified Close Translation as a Standard for MT. Accepted for poster presentation at the 10th Annual Conference of the European Association for Machine Translation, 30-31 May 2005, Budapest, Hungary.
Forsbom, Eva, Evaluation Report. Presented at Workshop on Machine Translation Evaluation: Human Evaluators Meet Automated Metrics (LREC'02), 27th May 2002.
Forsbom, Eva. 2003. Training a Super Model Look-Alike: Featuring Edit Distance, N-Gram Occurrence, and One Reference Translation. I Proceedings of 'Workshop on Machine Translation Evaluation: Towards Systemizing MT Evaluation' in conjunction with the Ninth Machine Translation Summit, New Orleans, USA, September 27, pp. 29--36.
Merkel, Magnus, Michael Petterstedt, Lars Ahrenberg: Interactive Word Alignment for Corpus Linguistics. Proceedings of Corpus Linguistics 2003. UCREL Technical Papers No 16, Part 1, pp. 533-542.
Sågvall Hein, Anna, Almqvist, Ingrid, Forsbom, Eva, Tiedemann, Jörg, Weijnitz, Per, Olsson, Leif-Jöran, Thaning, Sten, Scaling up an MT Prototype for Industrial Use. Databases and Data Flow. Third International Conference on Language Resources and Evaluation (LREC 2002), Las Palmas, 29-31 May 2002.
Sågvall Hein, Anna, Eva Forsbom, Per Weijnitz, Ebba Gustavii, and Jörg Tiedemann. MATS - A Glass Box Machine Translation System.Proceedings of MT Summit IX, New Orleans, 24-26 September 2003.
Tiedemann, Jörg, MatsLex - a Multilingual Lexical Database for Machine Translation Third International Conference on Language Resources and Evaluation (LREC 2002), Las Palmas, 29-31 May 2002. (Postscript, PDF)
Tiedemann, Jörg. Combining Clues for Word Alignment. In Proceedings of the 10th Conference of the European Chapter of the ACL (EACL03) Budapest, Hungary, April 12-17, 2003, pp. 339-346.
Tiedemann, Jörg and Lars Nygaard. The OPUS corpus - parallel and free. Proceedings of LREC'04. Vol. IV, pp. 1183-1186.
Tiedemann, Jörg, Optimization of word alignment parameters. Accepted for publication in Natrual Language Engineering, Special Issue on Parallell Texts, Cambridge University Press.
Weijnitz, Per, Eva Forsbom, Ebba Gustavii, Eva Pettersson, Jörg Tiedemann. MT goes farming: Comparing two machine translation approaches on a new domain. Proceedings of LREC'04, Vol. VI, pp. 2043-2046.
Presentations, abstracts and non-published reports
Ahrenberg, Lars, 2005. Sorting the chaff from the wheat in corpus-based machine translation. Accepted for poster presentation at Nodalida 2005, Joensuu, Finland, 19-20 May, 2005.
Forsbom, Eva, 2002. Utvärderingsansatser för MATS-systemet.
Forsbom, Eva, KOMA: Comparison of FTG codes and MATS codes. Technical Report. Uppsala University. Department of Linguistics.
Forsbom, Eva, 2003. Presentation at MT Summit IX.
Gustavii, Ebba och Eva Pettersson. 2003. Utveckling av ett svensk-engelskt lexikon för maskinöversättning inom jordbruksdomänen. Arbetsrapport, Uppsala universitet. Institutionen för lingvistik.
Holmqvist, Maria 2003. Översättningssystemet T4F - en implementation för ATIS-domänen.
Nyström, Mikael, Hans Åhlfeldt, Gunnar Klein, Gunnar Nilsson, Rong Chen, Lars Ahrenberg, Magnus Merkel och Michael Petterstedt, 2003: Halvautomatisk översättning av SNOMED CT till svenska. Posterpresentation vid konferensen "IT i vården - terminologi", arrangerad av Svensk Förening för Medicinsk Informatik, 5-6 november 2003.
Nygaard, Lars & Jörg Tiedemann. OPUS - an open source parallel corpus. Abstract of presentation at the 7th NoDaLiDa conference, Reykyavik, Iceland, 30-31 May, 2003.
Pettersson Eva, Pilotstudie om maskinöversättning inom ramen för Projekt Kursdatabas: Utveckling av språkliga resurser för ett vetenskapsområde samt utvärdering, 2005.
Tiedemann, Jörg, Catch the link! Combining Clues for Word Alignment. Invited presentation at the 7th TELRI Seminar in Dubrovnik, 26-28 September, 2002.
Doctoral theses related to the project
Jörg Tiedemann: Recycling Translations. Extraction of Lexical Data from Parallel Corpora and their Application in Natural Language Processing. Studia Linguistica Upsaliensia 1. Uppsala, 2003.
Master's theses related to the project
Maria Holmqvist, 2004. Identifying Translation Shifts Using Dependency Grammar and Interactive Word Alignment. Linköpings universitet, LIU-KOGVET-D--04/06--SE.
Jin Nie, 2003. Implementation and Evaluation of Decoder for Statistical Natural Language Translation. Linköpings universitet, LiTH-IDA-Ex--03/079--SE.
Markus Saers, Example-based Segmentation of Swedish Compounds in a Swedish-English bilingual corpus. Master's thesis in Computational Linguistics, Department of Linguistics and Philology, Uppsala University, 2005.
Xiaoyang Wang, 2004. Evaluation of Two Word Alignment Systems. Linköpings universitet, LiTH-IDA-Ex--04/019--SE.
KOMA
Latest update: 29 April, 2005.