LIG System for WMT13 QE Task: Investigating the Usefulness of Features in Word Confidence Estimation for MT

Abstract : This paper presents the LIG's systems submitted for Task 2 of WMT13 Quality Estimation campaign. This is a word confidence estimation (WCE) task where each participant was asked to label each word in a translated text as a binary (Keep/Change) or multi-class (Keep/Substitute/Delete) category. We integrate a number of features of various types (system-based, lexical, syntactic and semantic) into the conventional feature set, for our baseline classifier training. After the experiments with all features, we deploy a " Feature Selection " strategy to keep only the best performing ones. Then, a method that combines multiple " weak " classifiers to build a strong " composite " classifier by taking advantage of their complementarity is presented and experimented. We then select the best systems for submission and present the official results obtained.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [12 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00953773
Contributor : Laurent Besacier <>
Submitted on : Thursday, November 23, 2017 - 11:51:06 AM
Last modification on : Tuesday, February 12, 2019 - 1:31:30 AM

File

LIGSystemForWMT13_ok.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : hal-00953773, version 1

Collections

Citation

Ngoc-Quang Luong, Benjamin Lecouteux, Laurent Besacier. LIG System for WMT13 QE Task: Investigating the Usefulness of Features in Word Confidence Estimation for MT. 8th Workshop on Statistical Machine Translation, 2013, Sofia, Bulgaria. pp.386-391. ⟨hal-00953773⟩

Share

Metrics

Record views

143

Files downloads

67