Etienne Denoual


2007

pdf bib
Analogical translation of unknown words in a statistical machine translation framework
Etienne Denoual
Proceedings of Machine Translation Summit XI: Papers

pdf bib
The NICT/ATR speech translation system for IWSLT 2007
Andrew Finch | Etienne Denoual | Hideo Okuma | Michael Paul | Hirofumi Yamamoto | Keiji Yasuda | Ruiqiang Zhang | Eiichiro Sumita
Proceedings of the Fourth International Workshop on Spoken Language Translation

This paper describes the NiCT-ATR statistical machine translation (SMT) system used for the IWSLT 2007 evaluation campaign. We participated in three of the four language pair translation tasks (CE, JE, and IE). We used a phrase-based SMT system using log-linear feature models for all tracks. This year we decoded from the ASR n-best lists in the JE track and found a gain in performance. We also applied some new techniques to facilitate the use of out-of-domain external resources by model combination and also by utilizing a huge corpus of n-grams provided by Google Inc.. Using these resources gave mixed results that depended on the technique also the language pair however, in some cases we achieved consistently positive results. The results from model-interpolation in particular were very promising.

2006

pdf bib
The NiCT-ATR statistical machine translation system for IWSLT 2006
Ruiqiang Zhang | Hirofumi Yamamoto | Michael Paul | Hideo Okuma | Keiji Yasuda | Yves Lepage | Etienne Denoual | Daichi Mochihashi | Andrew Finch | Eiichiro Sumita
Proceedings of the Third International Workshop on Spoken Language Translation: Evaluation Campaign

2005

pdf bib
The Influence of Example-data Homogeneity on EBMT Quality
Etienne Denoual
Workshop on example-based machine translation

pdf bib
The ‘purest’ EBMT System Ever Built: No Variables, No Templates, No Training, Examples, Just Examples, Only Examples
Yves Lepage | Etienne Denoual
Workshop on example-based machine translation

We designed, implemented and assessed an EBMT system that can be dubbed the “purest ever built”: it strictly does not make any use of variables, templates or training, does not have any explicit transfer component, and does not require any preprocessing of the aligned examples. It uses a specific operation, namely proportional analogy, that implicitly neutralises divergences between languages and captures lexical and syntactical variations along the paradigmatic and syntagmatic axes without explicitly decomposing sentences into fragments. In an experiment with a test set of 510 input sentences and an unprocessed corpus of almost 160,000 aligned sentences in Japanese and English, we obtained BLEU, NIST and mWER scores of 0.53, 8.53 and 0.39 respectively, well above a baseline simulating a translation memory.

pdf bib
ALEPH: an EBMT system based on the preservation of proportional analogies between sentences across languages
Yves Lepage | Etienne Denoual
Proceedings of the Second International Workshop on Spoken Language Translation

pdf bib
BLEU in Characters: Towards Automatic MT Evaluation in Languages without Word Delimiters
Etienne Denoual | Yves Lepage
Companion Volume to the Proceedings of Conference including Posters/Demos and tutorial abstracts

pdf bib
The Influence of Data Homogeneity on NLP System Performance
Etienne Denoual
Companion Volume to the Proceedings of Conference including Posters/Demos and tutorial abstracts

pdf bib
Automatic generation of paraphrases to be used as translation references in objective evaluation measures of machine translation
Yves Lepage | Etienne Denoual
Proceedings of the Third International Workshop on Paraphrasing (IWP2005)