LIG System for Word Level QE task at WMT14

Abstract : This paper describes our Word-level QE system for WMT 2014 shared task on Spanish-English pair. Compared to WMT 2013, this year's task is different due to the lack of SMT setting information and additional resources. We report how we overcome this challenge to retain most of the important features which performed well last year in our system. Novel features related to the availability of multiple systems output (new point of this year) are also proposed and experimented along with baseline set. The system is optimized by several ways: tuning the classification threshold, combining with WMT 2013 data, and refining using Feature Selection strategy on our development set, before dealing with the test set for submission.
Document type :
Conference papers
Complete list of metadatas

Cited literature [10 references]  Display  Hide  Download

https://hal.inria.fr/hal-01002924
Contributor : Laurent Besacier <>
Submitted on : Tuesday, February 27, 2018 - 9:47:35 AM
Last modification on : Monday, July 8, 2019 - 3:09:02 PM
Long-term archiving on : Monday, May 28, 2018 - 11:07:33 AM

File

WMT2014.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01002924, version 1

Citation

Ngoc-Quang Luong, Laurent Besacier, Benjamin Lecouteux. LIG System for Word Level QE task at WMT14. Workshop on Machine Translation (WMT), Jun 2014, Baltimore, United States. ⟨hal-01002924⟩

Share

Metrics

Record views

246

Files downloads

240