Docent: A Document-Level Decoder for Phrase-Based Statistical Machine Translation

Christian Hardmeier; Sara Stymne; Jörg Tiedemann; Joakim Nivre

Docent: A Document-Level Decoder for Phrase-Based Statistical Machine Translation

Christian Hardmeier
, Sara Stymne
, Jörg Tiedemann
, Joakim Nivre

Uppsala University

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

Abstract

We describe Docent, an open-source decoder for statistical machine translation that breaks with the usual sentence-by-sentence paradigm and translates complete documents as units. By taking translation to the document level, our decoder can handle feature models with arbitrary discourse-wide dependencies and constitutes an essential infrastructure component in the quest for discourse-aware SMT models.

Original language	English
Title of host publication	Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics: System Demonstrations
Publication date	9 Aug 2013
Publication status	Published - 9 Aug 2013
Externally published	Yes

Keywords

Document-level translation
Statistical machine translation
Discourse-aware SMT
Feature models for SMT
Open-source decoder

Access to Document

https://www.diva-portal.org/smash/get/diva2:649088/fulltext01.pdf

Cite this

@inproceedings{50bc26ceebf54e15a2f8bcecf53276ef,

title = "Docent: A Document-Level Decoder for Phrase-Based Statistical Machine Translation",

abstract = "We describe Docent, an open-source decoder for statistical machine translation that breaks with the usual sentence-by-sentence paradigm and translates complete documents as units. By taking translation to the document level, our decoder can handle feature models with arbitrary discourse-wide dependencies and constitutes an essential infrastructure component in the quest for discourse-aware SMT models.",

keywords = "Document-level translation, Statistical machine translation, Discourse-aware SMT, Feature models for SMT, Open-source decoder",

author = "Christian Hardmeier and Sara Stymne and J{\"o}rg Tiedemann and Joakim Nivre",

year = "2013",

month = aug,

day = "9",

language = "English",

booktitle = "Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics: System Demonstrations",

}

Docent: A Document-Level Decoder for Phrase-Based Statistical Machine Translation. / Hardmeier, Christian; Stymne, Sara; Tiedemann, Jörg et al.
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics: System Demonstrations. 2013.

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

TY - GEN

T1 - Docent: A Document-Level Decoder for Phrase-Based Statistical Machine Translation

AU - Hardmeier, Christian

AU - Stymne, Sara

AU - Tiedemann, Jörg

AU - Nivre, Joakim

PY - 2013/8/9

Y1 - 2013/8/9

N2 - We describe Docent, an open-source decoder for statistical machine translation that breaks with the usual sentence-by-sentence paradigm and translates complete documents as units. By taking translation to the document level, our decoder can handle feature models with arbitrary discourse-wide dependencies and constitutes an essential infrastructure component in the quest for discourse-aware SMT models.

AB - We describe Docent, an open-source decoder for statistical machine translation that breaks with the usual sentence-by-sentence paradigm and translates complete documents as units. By taking translation to the document level, our decoder can handle feature models with arbitrary discourse-wide dependencies and constitutes an essential infrastructure component in the quest for discourse-aware SMT models.

KW - Document-level translation

KW - Statistical machine translation

KW - Discourse-aware SMT

KW - Feature models for SMT

KW - Open-source decoder

M3 - Article in proceedings

BT - Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics: System Demonstrations

ER -

Docent: A Document-Level Decoder for Phrase-Based Statistical Machine Translation

Abstract

Keywords

Access to Document

Fingerprint

Cite this