1 |
Using Alignment to detect associated multiword expressions in bilingual corpora. Session 6 - Translation and Natural Language Processing
|
|
|
|
In: Actes du colloque Tralogy : Anticiper les technologies pour la traduction ; Tralogy I. Métiers et technologies de la traduction : quelles convergences pour l'avenir ? ; https://hal.archives-ouvertes.fr/hal-02496037 ; Tralogy I. Métiers et technologies de la traduction : quelles convergences pour l'avenir ?, Mar 2011, Paris, France. 13p (2011)
|
|
BASE
|
|
Show details
|
|
2 |
Alignment Memories: A Useful Tool to Handle Phrase Alignment Bottleneck
|
|
|
|
In: CLA'2011: Computational Linguistics-Applications Conference ; https://hal-lirmm.ccsd.cnrs.fr/lirmm-00764092 ; CLA'2011: Computational Linguistics-Applications Conference, Oct 2011, Jachranka, Poland. pp.61-67 ; http://www.wikicfp.com/cfp/servlet/event.showcfp?eventid=15440©ownerid=834 (2011)
|
|
Abstract:
International audience ; This document presents two bilingual phrase-based alignment methods handling syntactic constituents (sub-sentential components) of parallel sentences. The methods rely on an asymmetrical parsing of both languages: Light part-of-speech tagging for the target language, syntactic tree building for the 'source' language and the complexity of each is studied. One of their benefits is that they do not require lexical knowledge for granting alignment. Another is that they align constituents of variable length and structure, thus providing information about divergent translations. Their originality rely on the fact that parsing of the supposed source language is reused both in resource building and alignment process. The models and methods can be seen as a subclass of Example Based Machine Translation. They built what can be called as an Alignment Mem- ory, the alignment correspondent of Translation Memories. The information acquisition process, partly supervised, is embedded in an online graphical human interface which accelerates the construction of golden corpora by one or many users.
|
|
Keyword:
[INFO.INFO-TT]Computer Science [cs]/Document and Text Processing; computational linguistics; data mining; natural language processing; semantics
|
|
URL: https://hal-lirmm.ccsd.cnrs.fr/lirmm-00764092/file/CLA2011.pdf https://hal-lirmm.ccsd.cnrs.fr/lirmm-00764092/document https://hal-lirmm.ccsd.cnrs.fr/lirmm-00764092
|
|
BASE
|
|
Hide details
|
|
3 |
Two Memory-Based Methods for Phrase Alignment
|
|
|
|
In: 5th Language and Technology Conference ; https://hal-lirmm.ccsd.cnrs.fr/lirmm-00838090 ; 5th Language and Technology Conference, Nov 2011, Poland. pp.101-110 ; http://www.ltc.amu.edu.pl/ (2011)
|
|
BASE
|
|
Show details
|
|
4 |
Automatic Titling of Articles Using Position and Statistical Information
|
|
|
|
In: RANLP'11: Recent Advances in Natural Language Processing ; https://hal-lirmm.ccsd.cnrs.fr/lirmm-00637975 ; RANLP'11: Recent Advances in Natural Language Processing, Dec 2011, Hissar, Bulgaria. pp.727-732 ; http://lml.bas.bg/ranlp2011/start3.php (2011)
|
|
BASE
|
|
Show details
|
|
5 |
Demo: Text Titling Application
|
|
|
|
In: Personal Semantic Data (EKAW'10 Demonstration) ; https://hal-lirmm.ccsd.cnrs.fr/lirmm-00563912 ; Personal Semantic Data (EKAW'10 Demonstration), Portugal. pp.N/A ; http://semanticweb.org/wiki/Personal_Semantic_Data (2011)
|
|
BASE
|
|
Show details
|
|
6 |
Automatic Titling of Electronic Documents with Noun Phrase Extraction
|
|
|
|
In: SOCPAR'10: SOft Computing and PAttern Recognition ; https://hal-lirmm.ccsd.cnrs.fr/lirmm-00563903 ; SOCPAR'10: SOft Computing and PAttern Recognition, France. pp.168-171 ; http://www.socpar.org/ (2011)
|
|
BASE
|
|
Show details
|
|
7 |
Managing Personal Information by Automatic Titling of E-mails
|
|
|
|
In: Personal Semantic Data (EKAW'10 Workshop) ; https://hal-lirmm.ccsd.cnrs.fr/lirmm-00563889 ; Personal Semantic Data (EKAW'10 Workshop), Lisbon, Portugal ; http://semanticweb.org/wiki/Personal_Semantic_Data (2011)
|
|
BASE
|
|
Show details
|
|
|
|