Zobrazeno 1 - 10
of 60
pro vyhledávání: '"Shumin Shi"'
Publikováno v:
CAAI Transactions on Intelligence Technology, Vol 8, Iss 1, Pp 118-128 (2023)
Abstract Emotion cause extraction (ECE) task that aims at extracting potential trigger events of certain emotions has attracted extensive attention recently. However, current work neglects the implicit emotion expressed without any explicit emotional
Externí odkaz:
https://doaj.org/article/1a6e72af509a4f84ba92d8fa88e0ca00
Publikováno v:
Applied Sciences, Vol 12, Iss 10, p 5003 (2022)
Theinference stage can be accelerated significantly using a Non-Autoregressive Transformer (NAT). However, the training objective used in the NAT model also aims to minimize the loss between the generated words and the golden words in the reference.
Externí odkaz:
https://doaj.org/article/d7ce05c894764420a1c4b602c837ce4d
Publikováno v:
ACM Transactions on Asian and Low-Resource Language Information Processing. 22:1-11
The Non-Autoregressive Transformer, due to its low inference latency, has attracted much attention from researchers. Although, the performance of the non-autoregressive transformer has been significantly improved in recent years, there is still a gap
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2c1a9a75ee4e8463f6d2ab57d582fa13
https://doi.org/10.1145/3587266
https://doi.org/10.1145/3587266
Publikováno v:
ACM Transactions on Asian and Low-Resource Language Information Processing. 21:1-22
Neural Machine Translation (NMT) brings promising improvements in translation quality, but until recently, these models rely on large-scale parallel corpora. As such corpora only exist on a handful of language pairs, the translation performance is fa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8edf1192d2f51643795e706c226de73a
https://doi.org/10.1145/3524300
https://doi.org/10.1145/3524300
Publikováno v:
ACM Transactions on Asian and Low-Resource Language Information Processing. 21:1-15
Statistical machine translation (SMT) models rely on word-, phrase-, and syntax-level alignments. But neural machine translation (NMT) models rarely explicitly learn the phrase- and syntax-level alignments. In this article, we propose to improve NMT
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::51e2e6241f9922cb28f061eabc02e7a2
https://doi.org/10.1145/3510580
https://doi.org/10.1145/3510580
Publikováno v:
CAAI Transactions on Intelligence Technology. 8:118-128
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::79e1d748a9f25e694f99af4ea1907399
https://doi.org/10.1049/cit2.12099
https://doi.org/10.1049/cit2.12099
Publikováno v:
2023 7th International Conference on Control Engineering and Artificial Intelligence.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b90ab2065ce8028c0fd502381d516b6f
https://doi.org/10.1145/3580219.3580231
https://doi.org/10.1145/3580219.3580231
With the development of Internet of Things and cloud computing, intelligent question-answering (QA) has brought great convenience to human's daily activities. As one of the core technologies, sentence semantic matching (SSM) plays a critical role in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::96cec96114e60fb66428816a0bdad8a2
https://hdl.handle.net/10453/164536
https://hdl.handle.net/10453/164536
Publikováno v:
Machine Translation. 35:595-609
Non-autoregressive machine translation aims to speed up the decoding procedure by discarding the autoregressive model and generating the target words independently. Because non-autoregressive machine translation fails to exploit target-side informati
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::44f8f9c9ccbad58bf920a098c6617c8b
https://doi.org/10.1007/s10590-021-09285-x
https://doi.org/10.1007/s10590-021-09285-x
Publikováno v:
2022 IEEE 8th International Conference on Cloud Computing and Intelligent Systems (CCIS).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a920786297f78c4552b0ece22fba8c67
https://doi.org/10.1109/ccis57298.2022.10016420
https://doi.org/10.1109/ccis57298.2022.10016420