Feature Weight Optimization for Discourse-Level SMT

Sara Stymne; Christian Hardmeier; Jörg Tiedemann; Joakim Nivre

Feature Weight Optimization for Discourse-Level SMT

Sara Stymne
, Christian Hardmeier
, Jörg Tiedemann
, Joakim Nivre

Uppsala University

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

Abstract

We present an approach to feature weight optimization for document-level decoding. This is an essential task for enabling future development of discourse-level statistical machine translation, as it allows easy integration of discourse features in the decoding process. We extend the framework of sentence-level feature weight optimization to the document-level. We show experimentally that we can get competitive and relatively stable results when using a standard set of features, and that this framework also allows us to optimize document-level features, which can be used to model discourse phenomena.

Original language	English
Title of host publication	Proceedings of the Workshop on Discourse in Machine Translation
Publication date	31 Aug 2013
Publication status	Published - 31 Aug 2013
Externally published	Yes

Keywords

Statistical machine translation
Document-level decoding
Feature weight optimization
Discourse features
Discourse phenomena

Access to Document

https://aclanthology.org/W13-3308.pdf

Cite this

@inproceedings{15b8afb1d16c4ffc9568af8a9efc6e42,

title = "Feature Weight Optimization for Discourse-Level SMT",

abstract = "We present an approach to feature weight optimization for document-level decoding. This is an essential task for enabling future development of discourse-level statistical machine translation, as it allows easy integration of discourse features in the decoding process. We extend the framework of sentence-level feature weight optimization to the document-level. We show experimentally that we can get competitive and relatively stable results when using a standard set of features, and that this framework also allows us to optimize document-level features, which can be used to model discourse phenomena.",

keywords = "Statistical machine translation, Document-level decoding, Feature weight optimization, Discourse features, Discourse phenomena",

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

year = "2013",

month = aug,

day = "31",

language = "English",

booktitle = "Proceedings of the Workshop on Discourse in Machine Translation",

}

TY - GEN

T1 - Feature Weight Optimization for Discourse-Level SMT

AU - Stymne, Sara

AU - Hardmeier, Christian

AU - Tiedemann, Jörg

AU - Nivre, Joakim

PY - 2013/8/31

Y1 - 2013/8/31

N2 - We present an approach to feature weight optimization for document-level decoding. This is an essential task for enabling future development of discourse-level statistical machine translation, as it allows easy integration of discourse features in the decoding process. We extend the framework of sentence-level feature weight optimization to the document-level. We show experimentally that we can get competitive and relatively stable results when using a standard set of features, and that this framework also allows us to optimize document-level features, which can be used to model discourse phenomena.

AB - We present an approach to feature weight optimization for document-level decoding. This is an essential task for enabling future development of discourse-level statistical machine translation, as it allows easy integration of discourse features in the decoding process. We extend the framework of sentence-level feature weight optimization to the document-level. We show experimentally that we can get competitive and relatively stable results when using a standard set of features, and that this framework also allows us to optimize document-level features, which can be used to model discourse phenomena.

KW - Statistical machine translation

KW - Document-level decoding

KW - Feature weight optimization

KW - Discourse features

KW - Discourse phenomena

M3 - Article in proceedings

BT - Proceedings of the Workshop on Discourse in Machine Translation

ER -

Feature Weight Optimization for Discourse-Level SMT

Abstract

Keywords

Access to Document

Fingerprint

Cite this