Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Shang‐Yu Su"'
Publikováno v:
SID Symposium Digest of Technical Papers. 53:54-57
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::99deae0f9167952da32aef016d457d44
https://doi.org/10.1002/sdtp.15414
https://doi.org/10.1002/sdtp.15414
Publikováno v:
SID Symposium Digest of Technical Papers. 53:1276-1279
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3dc42c10a78094198e3fdb4b1894a1fa
https://doi.org/10.1002/sdtp.15740
https://doi.org/10.1002/sdtp.15740
Publikováno v:
SID Symposium Digest of Technical Papers. 52:153-156
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5838adaef36dc88fff065c5b4e7bca57
https://doi.org/10.1002/sdtp.14634
https://doi.org/10.1002/sdtp.14634
Publikováno v:
EMNLP (Findings)
Natural language understanding (NLU) and Natural language generation (NLG) tasks hold a strong dual relationship, where NLU aims at predicting semantic labels based on natural language utterances and NLG does the opposite. The prior work mainly focus
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e98cae5bab7ed6c19348ea2a61b77126
http://arxiv.org/abs/2010.04246
http://arxiv.org/abs/2010.04246
Publikováno v:
EMNLP (1)
It is challenging to perform lifelong language learning (LLL) on a stream of different tasks without any performance degradation comparing to the multi-task counterparts. To address this issue, we present Lifelong Language Knowledge Distillation (L2K
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9294f42efe061cc1ed6aa937566a972c
http://arxiv.org/abs/2010.02123
http://arxiv.org/abs/2010.02123
Publikováno v:
ACL
In modular dialogue systems, natural language understanding (NLU) and natural language generation (NLG) are two critical components, where NLU extracts the semantics from the given texts and NLG is to construct corresponding natural language sentence
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5524609f797be4eac5890ab2a8bc3549
Publikováno v:
ICASSP
Amortized variational inference (AVI) enables efficient training of deep generative models to scale to large datasets. The quality of the approximate inference is determined by various reasons, such as the ability of producing proper variational para
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ee6529649250f7cdafb47be0fa520f0f
https://doi.org/10.1109/icassp.2019.8683633
https://doi.org/10.1109/icassp.2019.8683633
End-to-end dialogue generation has achieved promising results without using handcrafted features and attributes specific for each task and corpus. However, one of the fatal drawbacks in such approaches is that they are unable to generate informative
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::505ccb22b6f576c8ea4a74f2ea599a88
http://arxiv.org/abs/1903.09813
http://arxiv.org/abs/1903.09813
With increasing research interests in dialogue modeling, there is an emerging branch that formulates this task as next sentence selection, where given the partial dialogue context, the goal is to determine the most probable next sentence. To model na
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4eaad3b85d6386bfdc8648bb507fdb76
http://arxiv.org/abs/1903.08953
http://arxiv.org/abs/1903.08953