Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Shuoyang Ding"'
We propose a novel scheme to use the Levenshtein Transformer to perform the task of word-level quality estimation. A Levenshtein Transformer is a natural fit for this task: trained to perform decoding in an iterative manner, a Levenshtein Transformer
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::edb07fdc30bd7eeff4c59e70a72e088b
http://arxiv.org/abs/2109.05611
http://arxiv.org/abs/2109.05611
Autor:
Yiwen Shao, Nanyun Peng, Lei Xie, Yiming Wang, Hang Lv, Tongfei Chen, Sanjeev Khudanpur, Shuoyang Ding, Hainan Xu, Shinji Watanabe
Publikováno v:
ASRU
We present Espresso, an open-source, modular, extensible end-to-end neural automatic speech recognition (ASR) toolkit based on the deep learning library PyTorch and the popular neural machine translation toolkit fairseq. Espresso supports distributed
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e8bf3e2fa28e9b2d2cfe090063bd4cb4
https://doi.org/10.1109/asru46091.2019.9003968
https://doi.org/10.1109/asru46091.2019.9003968
Autor:
Philipp Koehn, Shuoyang Ding
Publikováno v:
SPNLP@NAACL-HLT
Stack Long Short-Term Memory (StackLSTM) is useful for various applications such as parsing and string-to-tree neural machine translation, but it is also known to be notoriously difficult to parallelize for GPU training due to the fact that the compu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::21a22e012b887759d17436f4bbc3eb54
Publikováno v:
WMT (1)
Despite their original goal to jointly learn to align and translate, Neural Machine Translation (NMT) models, especially Transformer, are often perceived as not learning interpretable word alignments. In this paper, we show that NMT models do learn i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b69d18d50c15bdecd023788a83c91112
https://doi.org/10.18653/v1/w19-5201
https://doi.org/10.18653/v1/w19-5201
Publikováno v:
INTERSPEECH
We present a new end-to-end architecture for automatic speech recognition (ASR) that can be trained using \emph{symbolic} input in addition to the traditional acoustic input. This architecture utilizes two separate encoders: one for acoustic input an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e136fa84b0dc152817cd377e7ccec7bf
http://arxiv.org/abs/1803.10299
http://arxiv.org/abs/1803.10299
Publikováno v:
WMT
Ding, S, Khayrallah, H, Koehn, P, Post, M, Kumar, G & Duh, K 2017, The JHU Machine Translation Systems for WMT 2017 . in Proceedings of the Conference on Machine Translation (WMT), Volume 2: Shared Task Papers . Copenhagen, Denmark, pp. 276-282, Second Conference on Machine Translation (WMT), Copenhagen, Denmark, 7/09/17 . < http://www.aclweb.org/anthology/W17-4724 >
Ding, S, Khayrallah, H, Koehn, P, Post, M, Kumar, G & Duh, K 2017, The JHU Machine Translation Systems for WMT 2017 . in Proceedings of the Conference on Machine Translation (WMT), Volume 2: Shared Task Papers . Copenhagen, Denmark, pp. 276-282, Second Conference on Machine Translation (WMT), Copenhagen, Denmark, 7/09/17 . < http://www.aclweb.org/anthology/W17-4724 >
This paper describes the Johns Hopkins University submissions to the sharedtranslation task of EMNLP 2017 Second Conference on Machine Translation(WMT 2017). We set up phrase-based, syntax-based and/or neural machine translation systems for all 14 la
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fde81ecda28a4964cd474cf1deaa3b43
https://doi.org/10.18653/v1/w17-4724
https://doi.org/10.18653/v1/w17-4724
Publikováno v:
WMT
Ding, S, Duh, K, Khayrallah, H, Koehn, P & Post, M 2016, The JHU Machine Translation Systems for WMT 2016 . in Proceedings of the First Conference on Machine Translation, Volume 2: Shared Task Papers . Berlin, Germany, pp. 272-280, First Conference on Machine Translation, Berlin, Germany, 11/08/16 . https://doi.org/10.18653/v1/W16-2310
Ding, S, Duh, K, Khayrallah, H, Koehn, P & Post, M 2016, The JHU Machine Translation Systems for WMT 2016 . in Proceedings of the First Conference on Machine Translation, Volume 2: Shared Task Papers . Berlin, Germany, pp. 272-280, First Conference on Machine Translation, Berlin, Germany, 11/08/16 . https://doi.org/10.18653/v1/W16-2310
This paper describes the submission of Johns Hopkins University for the shared translation task of ACL 2016 First Conference on Machine Translation (WMT 2016). We set up phrase-based, hierarchical phrase-based and syntax-based systems for all 12 lang
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c397ae0d17037b68b91791ba53678c05
https://doi.org/10.18653/v1/w16-2310
https://doi.org/10.18653/v1/w16-2310
Publikováno v:
ACL (1)
This paper is concerned with building linguistic resources and statistical parsers for deep grammatical relation (GR) analysis of Chinese texts. A set of linguistic rules is defined to explore implicit phrase structural information and thus build hig
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0d28bd3024c5106ffbe7d40971d5ce2f
https://doi.org/10.3115/v1/p14-1042
https://doi.org/10.3115/v1/p14-1042