Filters








3 Hits in 6.5 sec

Discourse in Statistical Machine Translation

Christian Hardmeier
2012 Discours  
This thesis addresses the technical and linguistic aspects of discourse-level processing in phrase-based statistical machine translation (SMT).  ...  We demonstrate the viability of this decoding approach for different document-level models. From a linguistic viewpoint, we focus on the problem of translating pronominal anaphora.  ...  In: Proceedings of the 16th Conference of the European Association for Machine Translation (EAMT), Trento (Italy), 261-268. C , J S. (1958). Readability: An appraisal of research and application.  ... 
doi:10.4000/discours.8726 fatcat:gxkpd2ubvzbjna7f7hw62oicg4

Why TEI stand-off annotation doesn't quite work

Piotr Bański
Proceedings of Balisage: The Markup Conference 2010   unpublished
Acknowledgments This work was supported by the EU Lifelong Learning Project KELLY. Much of the work discussed has been undertaken together with members of the KELLY team.  ...  In Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics (EACL'06), pages 16-23.  ...  In Proceedings of 13th Annual Conference of the European Association for Machine Translation (EAMT 2009). Resnik, P., & Smith, N.A. 2003. The Web as a parallel corpus.  ... 
doi:10.4242/balisagevol5.banski01 fatcat:am7p7jpr6bd6znxw4f3ew5p6va

Ivelina Nikolova and Natalia Konstantinova Organisers of the Student Workshop

Irina Temnikova, Natalia Konstantinova, Alexandra Balahur, Chris Biemann, Kevin Cohen, Darja Fišer, Najeh Hajlaoui, Laura Hasler, Sobha Lalitha, Devi, Wolfgang Maier, Preslav Nakov (+19 others)
unpublished
In this paper, we show how our methods developed for identifying light verb constructions can be adapted to different domains and different types of texts.  ...  We both experiment with rule-based methods and machine learning approaches.  ...  Acknowledgements The work reported in this paper laid the foundation of the "Applied Technology for Language-Aided CMS" project co-funded by the European Commission under the Information and Communications  ... 
fatcat:uxotu5b5mbh6jmf5wo4een7pda