BROWSE
Detail
Conference Paper
QEBERT: Bilingual BERT using Multi-task Learning for Neural Quality Estimation
Cited - time in 
Share 
Share
- Authors
- Hyun Kim, Joon-Ho Lim, Hyun-Ki Kim, Seung-Hoon Na
- Issue Date
- 2019-08
- Citation
- Conference on Machine Translation (WMT) 2019, pp.85-89
- Publisher
- Association for Computational Linguistics
- Language
- English
- Type
- Conference Paper
- Abstract
- For translation quality estimation at word and sentence levels, this paper presents a novel approach based on BERT that recently has achieved impressive results on various natural language processing tasks. Our proposed model is re-purposed BERT for the translation quality estimation and uses multi-task learning for the sentence-level task and word-level subtasks (i.e., source word, target word, and target gap). Experimental results on Quality Estimation shared task of WMT19 show that our systems show competitive results and provide significant improvements over the baseline.
- KSP Keywords
- Natural Language Processing, Novel approach, Proposed model, Quality estimation, Shared task, Translation quality, multi-task learning, word-level