Were the clocks striking or surprising?: using WSD to improve MT performance

Authors:
Špela Vintar;Darja Fišer;Aljoša Vrščaj
Affiliations:
University of Ljubljana, Ljubljana, Aškerčeva;University of Ljubljana, Ljubljana, Aškerčeva;University of Ljubljana, Ljubljana, Aškerčeva
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 7
Cited 0

Target Word Selection Using WordNet and Data-Driven Models in Machine Translation

PRICAI '02 Proceedings of the 7th Pacific Rim International Conference on Artificial Intelligence: Trends in Artificial Intelligence
Introduction to the special issue on evaluating word sense disambiguation systems

Natural Language Engineering
Distinguishing systems and distinguishing senses: new evaluation methods for Word Sense Disambiguation

Natural Language Engineering
Building a large ontology for machine translation

HLT '93 Proceedings of the workshop on Human Language Technology
Word-sense disambiguation for machine translation

HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
Personalizing PageRank for word sense disambiguation

EACL '09 Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics
Data-driven semantic analysis for multilingual WSD and lexical selection in translation

EACL '09 Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

We report on a series of experiments aimed at improving the machine translation of ambiguous lexical items by using wordnet-based unsupervised Word Sense Disambiguation (WSD) and comparing its results to three MT systems. Our experiments are performed for the English-Slovene language pair using UKB, a freely available graph-based word sense disambiguation system. Results are evaluated in three ways: a manual evaluation of WSD performance from MT perspective, an analysis of agreement between the WSD-proposed equivalent and those suggested by the three systems, and finally by computing BLEU, NIST and METEOR scores for all translation versions. Our results show that WSD performs with a MT-relevant precision of 71% and that 21% of sense-related MT errors could be prevented by using unsupervised WSD.