Using sense-labeled discourse connectives for statistical machine translation

Authors:
Thomas Meyer;Andrei Popescu-Belis
Affiliations:
Idiap Research Institute Rue Marconi, Martigny, Switzerland;Idiap Research Institute Rue Marconi, Martigny, Switzerland
Venue:
EACL 2012 Proceedings of the Joint Workshop on Exploiting Synergies between Information Retrieval and Machine Translation (ESIRMT) and Hybrid Approaches to Machine Translation (HyTra)
Year:
2012

Citing 17
Cited 1

WordNet: a lexical database for English

Communications of the ACM
The Theory and Practice of Discourse Parsing and Summarization

The Theory and Practice of Discourse Parsing and Summarization
An Adapted Lesk Algorithm for Word Sense Disambiguation Using WordNet

CICLing '02 Proceedings of the Third International Conference on Computational Linguistics and Intelligent Text Processing
A systematic comparison of various statistical alignment models

Computational Linguistics
BLEU: a method for automatic evaluation of machine translation

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Minimum error rate training in statistical machine translation

ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Optimization, maxent models, and conditional estimation without magic

NAACL-Tutorials '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology: Tutorials - Volume 5
Coarse-to-fine n-best parsing and MaxEnt discriminative reranking

ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Discourse Connective Argument Identification with Connective Specific Rankers

ICSC '08 Proceedings of the 2008 IEEE International Conference on Semantic Computing
Moses: open source toolkit for statistical machine translation

ACL '07 Proceedings of the 45th Annual Meeting of the ACL on Interactive Poster and Demonstration Sessions
Sequence models and ranking methods for discourse parsing

Sequence models and ranking methods for discourse parsing
Temporal processing with the TARSQI toolkit

COLING '08 22nd International Conference on on Computational Linguistics: Demonstration Papers
Disambiguating "DE" for Chinese-English machine translation

StatMT '09 Proceedings of the Fourth Workshop on Statistical Machine Translation
Classification of discourse coherence relations: an exploratory study using multiple knowledge sources

SigDIAL '06 Proceedings of the 7th SIGdial Workshop on Discourse and Dialogue
Using syntax to disambiguate explicit discourse connectives in text

ACLShort '09 Proceedings of the ACL-IJCNLP 2009 Conference Short Papers
Significance tests of automatic machine translation evaluation metrics

Machine Translation
How comparable are parallel corpora? Measuring the distribution of general vocabulary and connectives

BUCC '11 Proceedings of the 4th Workshop on Building and Using Comparable Corpora: Comparable Corpora and the Web

Assessing the accuracy of discourse connective translations: validation of an automatic metric

CICLing'13 Proceedings of the 14th international conference on Computational Linguistics and Intelligent Text Processing - Volume 2

Quantified Score

Hi-index	0.00

Visualization

Abstract

This article shows how the automatic disambiguation of discourse connectives can improve Statistical Machine Translation (SMT) from English to French. Connectives are firstly disambiguated in terms of the discourse relation they signal between segments. Several classifiers trained using syntactic and semantic features reach state-of-the-art performance, with F1 scores of 0.6 to 0.8 over thirteen ambiguous English connectives. Labeled connectives are then used into SMT systems either by modifying their phrase table, or by training them on labeled corpora. The best modified SMT systems improve the translation of connectives without degrading BLEU scores. A threshold-based SMT system using only high-confidence labels improves BLEU scores by 0.2--0.4 points.