The Uppsala-FBK systems at WMT 2011

Christian Hardmeier; Jörg Tiedemann; Markus Saers; Marcello Federico; Prashant Mathur

The Uppsala-FBK systems at WMT 2011

Christian Hardmeier, Jörg Tiedemann, Markus Saers, Marcello Federico, Prashant Mathur

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper presents our submissions to the shared translation task at WMT 2011. We created two largely independent systems for English-to-French and Haitian Creole-to-English translation to evaluate different features and components from our ongoing research on these language pairs. Key features of our systems include anaphora resolution, hierarchical lexical reordering, data selection for language modelling, linear transduction grammars for word alignment and syntax-based decoding with monolingual dependency information.

Original language	English
Title of host publication	Proceedings of the Sixth Workshop on Statistical Machine Translation
Place of Publication	Edinburgh, Scotland
Publisher	Association for Computational Linguistics
Pages	372-378
Number of pages	7
ISBN (Electronic)	978-1-937284-12-1
Publication status	Published - 31 Jul 2011
Event	Sixth Workshop on Statistical Machine Translation - Edinburgh, United Kingdom Duration: 30 Jul 2011 → 31 Jul 2011

Workshop

Workshop	Sixth Workshop on Statistical Machine Translation
Country/Territory	United Kingdom
City	Edinburgh
Period	30/07/11 → 31/07/11

Access to Document

The Uppsala-FBK_HARDMEIER_DOA17062011_VOR_CC-BYFinal published version, 123 KBLicence: Creative Commons: Attribution-NonCommercial-ShareAlike (CC BY-NC-SA)

https://www.aclweb.org/anthology/W11-2144Licence: Creative Commons: Attribution-NonCommercial-ShareAlike (CC BY-NC-SA)

Cite this

@inproceedings{55d80d8d90494954918f2032c26b6034,

title = "The Uppsala-FBK systems at WMT 2011",

abstract = "This paper presents our submissions to the shared translation task at WMT 2011. We created two largely independent systems for English-to-French and Haitian Creole-to-English translation to evaluate different features and components from our ongoing research on these language pairs. Key features of our systems include anaphora resolution, hierarchical lexical reordering, data selection for language modelling, linear transduction grammars for word alignment and syntax-based decoding with monolingual dependency information.",

author = "Christian Hardmeier and J{\"o}rg Tiedemann and Markus Saers and Marcello Federico and Prashant Mathur",

year = "2011",

month = jul,

day = "31",

language = "English",

pages = "372--378",

booktitle = "Proceedings of the Sixth Workshop on Statistical Machine Translation",

publisher = "Association for Computational Linguistics",

note = "Sixth Workshop on Statistical Machine Translation ; Conference date: 30-07-2011 Through 31-07-2011",

}

Hardmeier, C, Tiedemann, J, Saers, M, Federico, M & Mathur, P 2011, The Uppsala-FBK systems at WMT 2011. in Proceedings of the Sixth Workshop on Statistical Machine Translation. Association for Computational Linguistics, Edinburgh, Scotland, pp. 372-378, Sixth Workshop on Statistical Machine Translation, Edinburgh, United Kingdom, 30/07/11. <https://www.aclweb.org/anthology/W11-2144>

TY - GEN

T1 - The Uppsala-FBK systems at WMT 2011

AU - Hardmeier, Christian

AU - Tiedemann, Jörg

AU - Saers, Markus

AU - Federico, Marcello

AU - Mathur, Prashant

PY - 2011/7/31

Y1 - 2011/7/31

N2 - This paper presents our submissions to the shared translation task at WMT 2011. We created two largely independent systems for English-to-French and Haitian Creole-to-English translation to evaluate different features and components from our ongoing research on these language pairs. Key features of our systems include anaphora resolution, hierarchical lexical reordering, data selection for language modelling, linear transduction grammars for word alignment and syntax-based decoding with monolingual dependency information.

AB - This paper presents our submissions to the shared translation task at WMT 2011. We created two largely independent systems for English-to-French and Haitian Creole-to-English translation to evaluate different features and components from our ongoing research on these language pairs. Key features of our systems include anaphora resolution, hierarchical lexical reordering, data selection for language modelling, linear transduction grammars for word alignment and syntax-based decoding with monolingual dependency information.

M3 - Conference contribution

SP - 372

EP - 378

BT - Proceedings of the Sixth Workshop on Statistical Machine Translation

PB - Association for Computational Linguistics

CY - Edinburgh, Scotland

T2 - Sixth Workshop on Statistical Machine Translation

Y2 - 30 July 2011 through 31 July 2011

ER -

The Uppsala-FBK systems at WMT 2011

Abstract

Workshop

Access to Document

Fingerprint

Cite this