Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Shanbo Cheng"'
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 12 (2024)
Externí odkaz:
https://doaj.org/article/b147a1f6cb204cb08e83fdc13617aca8
Aiming to improve the Automatic Speech Recognition (ASR) outputs with a post-processing step, ASR error correction (EC) techniques have been widely developed due to their efficiency in using parallel text data. Previous works mainly focus on using te
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cf530896bde743da7360815611f676ec
http://arxiv.org/abs/2303.10160
http://arxiv.org/abs/2303.10160
The punctuation restoration task aims to correctly punctuate the output transcriptions of automatic speech recognition systems. Previous punctuation models, either using text only or demanding the corresponding audio, tend to be constrained by real s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c09e51dff6766ec463ce1ace17ebf163
http://arxiv.org/abs/2202.00468
http://arxiv.org/abs/2202.00468
Publikováno v:
ACL/IJCNLP (Findings)
Multilingual Neural Machine Translation (MNMT) has aroused widespread interest due to its efficiency. An exciting advantage of MNMT models is that they could also translate between unsupervised (zero-shot) language directions. Language tag (LT) strat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::470bfe38948e38ce5c90635d3839e6ae
Publikováno v:
ACL
Multilingual neural machine translation (NMT) has led to impressive accuracy improvements in low-resource scenarios by sharing common linguistic information across languages. However, the traditional multilingual model fails to capture the diversity
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6f907d8a1164c33e5997c41598dfffd0
https://doi.org/10.18653/v1/2020.acl-main.150
https://doi.org/10.18653/v1/2020.acl-main.150
Publikováno v:
AAAI
Pre-training and fine-tuning have achieved great success in natural language process field. The standard paradigm of exploiting them includes two steps: first, pre-training a model, e.g. BERT, with a large scale unlabeled monolingual data. Then, fine
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ebca98689bbffb8fdee34ee5266ab37f
Autor:
Shenglan Wu, Shanbo Cheng, Boxing Chen, Pei Zhang, Liang Yao, Jun Lu, Haibo Zhang, Guchun Zhang, Yongchao Deng, Changfeng Zhu, Jingang Wang, Kai Song
Publikováno v:
WMT (shared task)
This paper describes the submission systems of Alibaba for WMT18 shared news translation task. We participated in 5 translation directions including English ↔ Russian, English ↔ Turkish in both directions and English → Chinese. Our systems are
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::081841acd665a28fa7043c646e821d02
https://doi.org/10.18653/v1/w18-6408
https://doi.org/10.18653/v1/w18-6408
Autor:
Chen Wei, Yang Jiajun, Hongtao Yang, Lin Shi, Wang Yuguang, Shanbo Cheng, Jiang Liyang, Muze Li, Wang Yanfeng
Publikováno v:
WMT
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2c7e1c4c28b672de316d3672d0fce6ad
https://doi.org/10.18653/v1/w17-4742
https://doi.org/10.18653/v1/w17-4742
Publikováno v:
HLT-NAACL
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f2336e6aa31699d1cf661bcf4e292846
https://doi.org/10.18653/v1/n16-1148
https://doi.org/10.18653/v1/n16-1148