Automated Paraphrase Lattice Creation for HyTER Machine Translation Evaluation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

Automated Paraphrase Lattice Creation for HyTER Machine Translation Evaluation

Résumé

We propose a variant of a well-known machine translation (MT) evaluation metric, HyTER (Dreyer and Marcu, 2012), which exploits reference translations enriched with meaning equivalent expressions. The original HyTER metric relied on hand-crafted paraphrase networks which restricted its applicability to new data. We test, for the first time, HyTER with automatically built paraphrase lattices. We show that although the metric obtains good results on small and carefully curated data with both manually and automatically selected substitutes, it achieves medium performance on much larger and noisier datasets, demonstrating the limits of the metric for tuning and evaluation of current MT systems.
Fichier principal
Vignette du fichier
N18-2077.pdf (226.69 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-01838521 , version 1 (15-12-2022)

Identifiants

Citer

Marianna Apidianaki, Guillaume Wisniewski, Anne Cocos, Chris Callison-Burch. Automated Paraphrase Lattice Creation for HyTER Machine Translation Evaluation. Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics Jun 2018, Nouvelle Orléans, United States. pp.480 - 485, ⟨10.18653/v1/N18-1019⟩. ⟨hal-01838521⟩
43 Consultations
16 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More