Translate-train embracing translationese artifacts
Translate-train is a general training approach to multilingual tasks. The key idea is to use the translator of the target language to generate training data to mitigate the gap between the source and target languages. However, its performance is often hampered by the artifacts in the translated text...
Saved in:
Main Authors: | YU, Sicheng, SUN, Qianru, ZHANG, Hao, JIANG, Jing |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2022
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/7475 https://ink.library.smu.edu.sg/context/sis_research/article/8478/viewcontent/2022.acl_short.40.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Cross-thought for sentence encoder pre-training
by: WANG, Shuohang, et al.
Published: (2020) -
VLStereoSet: A study of stereotypical bias in pre-trained vision-language models
by: ZHOU, Kankan, et al.
Published: (2022) -
A BERT-based dual embedding model for Chinese idiom prediction
by: TAN, Minghuan, et al.
Published: (2020) -
Does BERT understand idioms? A probing-based empirical study of BERT encodings of idioms
by: TAN, Minghuan, et al.
Published: (2021) -
Can syntax help? Improving an LSTM-based Sentence Compression Model for New Domains
by: WANG, Liangguo, et al.
Published: (2017)