Keywords

Authors

Year

Publications

The publications database contains papers and technical reports written by XRCE scientists from 1991 up to the present. If the document you are looking for cannot be downloaded in PDF or Postscript format, please contact us specifying the title, author(s) and reference. Any document downloaded from the publications database may be used for non-commercial purposes only.


Productive Generation of Compound Words in Statistical Machine Translation

Sara Stymne, Nicola Cancedda

EMNLP, 6th Workshop on Statistical Machine Translation, Edinburgh, UK, July 30-31.

Ref. : 2011/015  |  Abstract


Confidence-Weighted Learning of Factored Discriminative Language Models

Viet Ha-Thuc, Nicola Cancedda

ACL/HLT 2011, June 19-24, 2011, Portland, Oregon, USA.

Ref. : 2011/010  |  Abstract


Minimum Error Rate Training by Sampling the Translation Lattice

Samidh Chatterjee, Nicola Cancedda

EMNLP (Conference on Empirical Methods for Natural Language Processing), MIT Stata Center, Massachusetts, USA, 9-11 October 2010

Ref. : 2010/037  |  Abstract


On the intersection of hierarchical and phase-besed models of translations

Marc Dymetman, Nicola Cancedda

Fourth Workshop on Syntax and Structure in statistical Translation (SSST-4) colocated with Coling 2010, Beijing, China, 28 August 2010 Full paper available on SSST Website

Ref. : 2010/036  |  Abstract


Machine Translation Using Overlapping Alignments and Sample Rank

Benjamin Roth, Andrew McCallum, Marc Dymetman, Nicola Cancedda

AMTA (Association for Machine Translation in the Americas), October 31 - November 5, 2010, Denver, Colorado, USA Full paper available on AMTA Website

Ref. : 2010/025  |  Abstract


Learning an Expert from Human Annotations in Statistical Machine Translation: the Case of Out-of-Vocabulary Words

Aziz Wilker, Marc Dymetman, Lucia Specia, Mirkin Shachar, Ido Dagan, Nicola Cancedda

EAMT 2010 - 4th Annual Conference of the European Association for Machine Translation - Saint-Raphaƫl, France, May 27-28, 2010.

Ref. : 2010/008  |  Abstract


A Dataset for Assessing Machine Translation Evaluation Metrics

Lucia Specia, Nicola Cancedda, Marc Dymetman

LREC 2010 (Seventh international conference on Language Resources and Evaluation), Malta, 17-23 May 2010
Full paper available on LREC 2010 website

Ref. : 2009/084  |  Abstract


Complexity Based Phrase-Table Filtering for Statistical Machine Translation

Nadi Tomeh, Nicola Cancedda, Marc Dymetman

MT Summit 2009 (Machine Translation Summit XII), Ottawa, Ontario, Canada, August 26-30, 2009.
Full paper available on MT Summit Website

Ref. : 2009/038  |  Abstract  |  2009-038.pdf (223.42 kB)


Phrase-Based Statistical Machine Translation as a Travelling Salesman Problem

Mikhail Zaslavski, Marc Dymetman, Nicola Cancedda

ACL-IJCNLP 2009 (Association for Computational Linguistics and International Joint Conference on Natural Language Processing), Suntec, Singapore, 2-7 August 2009

Ref. : 2009/017  |  Abstract


Source-Language Entailment Modeling for Translating Unknown Terms

Lucia Specia, Shachar Mirkin, Ido Dagan, Idan Szpekti, Marc Dymetman, Nicola Cancedda

ACL-IJCNLP 2009 (Association for Computational Linguistics and International Joint Conference on Natural Language Processing), Suntec, Singapore, 2-7 August 2009

Ref. : 2009/016  |  Abstract