Filters








4,245 Hits in 4.8 sec

French-English Terminology Extraction from Comparable Corpora [chapter]

Béatrice Daille, Emmanuel Morin
2005 Lecture Notes in Computer Science  
First, this method extracts MWTs in each language, and then uses statistical methods to align single words and MWTs by exploiting the term contexts.  ...  Finally, we evaluate our approach and demonstrate its significance, particularly in relation to non-compositional MWT alignment.  ...  Acknowledgements We are particularly grateful to Samuel Dufour-Kowalski, who undertook the computer programs. This work has also benefited from his comments.  ... 
doi:10.1007/11562214_62 fatcat:cmbdysk43nfz7bb6lh33po7rme

A statistical approach to crosslingual natural language tasks

David Pinto, Jorge Civera, Alberto Barrón-Cedeño, Alfons Juan, Paolo Rosso
2009 Journal of Algorithms  
We propose to use a statistical approach in order to tackle the problem of dealing with crosslingual natural language tasks.  ...  In particular, we apply the IBM alignment model 1 with the aim of obtaining a statistical bilingual dictionary which may further be used in order to approximate the relatedness probability of two given  ...  Acknowledgments The authors would like to thank Raphael Salkie of the University of Brighton for providing access to the INTERSECT corpus.  ... 
doi:10.1016/j.jalgor.2009.02.005 fatcat:sghtwjk5uzhurjg3yifyo7kl3i

Towards accurate predictors of word quality for Machine Translation: Lessons learned on French–English and English–Spanish systems

Ngoc-Quang Luong, Laurent Besacier, Benjamin Lecouteux
2015 Data & Knowledge Engineering  
The classifiers are built over two different bilingual corpora: French -English (fr-en) and English -Spanish (en-es).  ...  Unlike most of previous work, the authors in [7] apply solely external features with the hope that their classifier can deal with various MT approaches, from statistical-based to rule-based.  ...  A novel approach introduced in [5] explicitly explores the phrase-based translation model for detecting word errors.  ... 
doi:10.1016/j.datak.2015.04.003 fatcat:ypelfik5ezhardyzpnkcf3dxxi

Quantum, a French/English Cross-Language Question Answering System [chapter]

Luc Plamondon, George Foster
2004 Lecture Notes in Computer Science  
Our method relies on a statistical translation engine to translate keywords, and a set of manually written rules for analyzing French questions.  ...  We describe a method for modifying a monolingual English question answering system to allow it to accept French questions.  ...  We would also like to thank Elliott Macklovitch and Guy Lapalme from the RALI, and Joel Martin from the NRC, for their help in conducting this research.  ... 
doi:10.1007/978-3-540-30222-3_53 fatcat:2rifhygq5rdezlxwq2pbr2o6ae

Alignment of comparable documents: Comparison of similarity measures on French–English–Arabic data

D. LANGLOIS, M. SAAD, K. SMAILI
2018 Natural Language Engineering  
To build such corpus, we propose to use the Cross-Lingual Latent Semantic approach.  ...  A recall at rank 1 of 50.16 per cent is achieved with the Cross-lingual LSI approach for BBC–JSC test corpus, while the dictionary-based method reaches a recall of only 35.41 per cent.  ...  For the bilingual dictionaries, we used Euradic Sci-Fran 6 for French-English and a dictionary extracted from Multilingual WordNet for Arabic-English.  ... 
doi:10.1017/s1351324918000232 fatcat:qulmfx2ujbelbc2k5sivychmwq

German, French, English and Persian Retrieval Experiments at CLEF 2008

Stephen Tomlinson
2008 Conference and Labs of the Evaluation Forum  
We describe evaluation experiments conducted by submitting retrieval runs for the monolingual German, French, English and Persian (Farsi) information retrieval tasks of the Ad-Hoc Track of the Cross-Language  ...  Also, for each language, we submitted a sample of the first 10000 retrieved items to investigate the frequency of relevant items at deeper ranks than the official judging depth of 60.  ...  Methodology Data The CLEF 2008 Ad-Hoc Track document sets consisted of tagged (XML-formatted) records or documents in 4 different languages: German, French, English and Persian (also known as Farsi).  ... 
dblp:conf/clef/Tomlinson08a fatcat:ev6zhii7yfgtlhb2lcnxbgdioy

German, French, English and Persian Retrieval Experiments at CLEF 2009

Stephen Tomlinson
2009 Conference and Labs of the Evaluation Forum  
We describe evaluation experiments conducted by submitting retrieval runs for the monolingual German, French, English and Persian (Farsi) information retrieval tasks of the Ad Hoc Track of the Cross-Language  ...  In the ad hoc retrieval tasks, the system was given 50 natural language queries, and the goal was to find all of the relevant records or documents (with high precision) in a particular document set.  ...  We described evaluation experiments conducted by submitting retrieval runs for the monolingual German, French, English and Persian (Farsi) information retrieval tasks of the Ad Hoc Track of the Cross-Language  ... 
dblp:conf/clef/Tomlinson09a fatcat:fsbtupyovnh5xjxamqnxd66cwe

Aligning words in French-English non-parallel medical texts: effect of term frequency distributions

Yun-Chuang Chiao, Pierre Zweigenbaum
2004 Studies in Health Technology and Informatics  
In this paper, we present a method for aligning words based on a statistical model of word distribution similarity.  ...  Using automatically downloaded pages from different medical web sites and a combined bilingual lexicon of general and medical terms as language sources, a similarity score is assigned to each proposed  ...  Acknowledgments We would like to acknowledge Jean-David Sta for his useful help and comments during this work.  ... 
pmid:15360767 fatcat:mcgtnnodvjdczjnpqvw6lbupuy

Mood and modality in finite noun complement clauses: A French-English contrastive study

2010 International Journal of Corpus Linguistics  
Contrastive analysis of French and English provides evidence to substantiate these claims.  ...  On the one hand, we claim on the basis of cross-linguistic and semantic evidence that modality is a common intrinsic feature of nouns that licensethat/quecomplement clauses, and, as a consequence, that  ...  In fact, contrary to the approaches discussed so far, other analyses assume that modality appears to be a property which plays a significant role in the selection of head nouns in that-clauses.  ... 
doi:10.1075/ijcl.15.2.06kan fatcat:4gy4qov5w5cfhj3vqvmg5hhaua

Unsupervised Statistical Machine Translation [article]

Mikel Artetxe, Gorka Labaka, Eneko Agirre
2018 arXiv   pre-print
While modern machine translation has relied on large parallel corpora, a recent line of work has managed to train Neural Machine Translation (NMT) systems from monolingual corpora only (Artetxe et al.,  ...  In this paper, we propose an alternative approach based on phrase-based Statistical Machine Translation (SMT) that significantly closes the gap with supervised systems.  ...  Mikel Artetxe enjoys a doctoral grant from the Spanish MECD.  ... 
arXiv:1809.01272v1 fatcat:vh5rbftznrezjo5d5ciosbd7qu

Unsupervised Statistical Machine Translation

Mikel Artetxe, Gorka Labaka, Eneko Agirre
2018 Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing  
While modern machine translation has relied on large parallel corpora, a recent line of work has managed to train Neural Machine Translation (NMT) systems from monolingual corpora only (Artetxe et al.,  ...  In this paper, we propose an alternative approach based on phrase-based Statistical Machine Translation (SMT) that significantly closes the gap with supervised systems.  ...  Mikel Artetxe enjoys a doctoral grant from the Spanish MECD.  ... 
doi:10.18653/v1/d18-1399 dblp:conf/emnlp/ArtetxeLA18 fatcat:5m7ed7n23ncfrm6sitzjdov2jq

Unsupervised Neural Machine Translation [article]

Mikel Artetxe, Gorka Labaka, Eneko Agirre, Kyunghyun Cho
2018 arXiv   pre-print
Despite the simplicity of the approach, our system obtains 15.56 and 10.21 BLEU points in WMT 2014 French-to-English and German-to-English translation.  ...  In spite of the recent success of neural machine translation (NMT) in standard benchmarks, the lack of large parallel corpora poses a major practical problem for many language pairs.  ...  Mikel Artetxe enjoys a doctoral grant from the Spanish MECD.  ... 
arXiv:1710.11041v2 fatcat:fhjnfqm5dbfgni52cumslnr4xy

LIMSI$@$WMT'15 : Translation Task

Benjamin Marie, Alexandre Allauzen, Franck Burlot, Quoc-Khanh Do, Julia Ive, elena knyazeva, Matthieu Labeau, Thomas Lavergne, Kevin Löser, Nicolas Pécheux, François Yvon
2015 Proceedings of the Tenth Workshop on Statistical Machine Translation  
This paper describes LIMSI's submissions to the shared WMT'15 translation task. We report results for French-English, Russian-English in both directions, as well as for Finnish-into-English.  ...  The main novelties of this year's participation are the following: for Russian-English, we investigate a tailored normalization of Russian to translate into English, and a two-step process to translate  ...  Acknowledgements We would like to thank the anonymous reviewers for their helpful comments and suggestions.  ... 
doi:10.18653/v1/w15-3016 dblp:conf/wmt/MarieABDIKLLLPY15 fatcat:yn4cvlkwfragpdbpg3seuzmrzq

A statistical approach to language translation

P. Brown, J. Cocke, S. Della Pietra, V. Della Pietra, F. Jelinek, R. Mercer, P. Roossin
1988 Proceedings of the 12th conference on Computational linguistics -   unpublished
An approach to automatic translation is outlined that utilizes technklues of statistical inl'ormatiml extraction from large data bases.  ...  While wc are not yet able to provide examples of French / English tcanslation, we present some encouraging intermediate results concerning glossary creation and the arrangement of target WOl'd seq lie)  ...  Ill what follows we will not be able to give actual results el French / English translation: our less than a year old project is not I'ar enongh ahmg.  ... 
doi:10.3115/991635.991651 fatcat:7kf7mpqwfzaw7mhydusymbin6q

Orthography plays a critical role in cognate priming: Evidence from French/English and Arabic/French cognates

Jeffrey S. Bowers, Zohra Mimouni, Martin Arguin
2000 Memory & Cognition  
Perhaps the orthographic system fails to explicitly link the French/English as well as the Arabic/French cognates, and the modality-specific French/ English cognate priming reflects specific processes  ...  A set of 60 orthographically similar (but nonidentical) French! English cognates was selected for the experiment.  ... 
doi:10.3758/bf03211829 pmid:11219956 fatcat:s5267iozwbf4zmmtvzmzsjis2q
« Previous Showing results 1 — 15 out of 4,245 results