Show simple item record

dc.contributor.authorNicolas L
dc.contributor.authorStemle EW
dc.contributor.authorKranebitter K
dc.contributor.authorLyding V
dc.date.accessioned2019-03-01T12:59:48Z
dc.date.available2019-03-01T12:59:48Z
dc.date.issued2013
dc.identifier.urihttp://aclweb.org/anthology/R/R13/R13-1068.pdf
dc.identifier.urihttp://hdl.handle.net/10863/8838
dc.description.abstractIn this paper, we report on an unsupervised greedy-style process for acquiring phrase translations from sentence-aligned parallel corpora. Thanks to innovative selection strategies, this process can acquire multiple translations without size criteria, i.e. phrases can have several translations, can be of any size, and their size is not considered when selecting their translations. Even though the process is in an early development stage and has much room for improvements, evaluation shows that it yields phrase translations of high precision that are relevant to machine translation but also to a wider set of applications including memory-based translation or multi-word acquisition.en_US
dc.languageEnglish
dc.language.isoenen_US
dc.publisherRANLP 2011 Organising Committee / ACLen_US
dc.relationRecent Advances in Natural Language Processing (RANLP) 2013 ; Hissar : 7.9.2013 - 13.9.2013
dc.rights
dc.titleHigh-Accuracy Phrase Translation Acquisition Through Battle-Royale Selectionen_US
dc.typeBook chapteren_US
dc.date.updated2019-03-01T11:45:16Z
dc.publication.title
dc.language.isiEN-GB
dc.description.fulltextnoneen_US


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record