Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Yuanmeng Yan"'
Publikováno v:
IEEE Access, Vol 8, Pp 29407-29416 (2020)
Recently conversational agents effectively improve their understanding capabilities by neural networks. Such deep neural models, however, do not apply to most human languages due to the lack of annotated training data for various NLP tasks. In this p
Externí odkaz:
https://doaj.org/article/26db869829024f3d95e2c3f636bc3626
Publikováno v:
Neurocomputing. 445:267-275
Neural-based context-aware models for slot tagging tasks in language understanding have achieved state-of-the-art performance, especially deep contextualized models, such as ELMo, BERT. However, the presence of out-of-vocab (OOV) words significantly
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::962846d85eb49c9b0421ba51167260c9
https://doi.org/10.1016/j.neucom.2021.01.134
https://doi.org/10.1016/j.neucom.2021.01.134
Autor:
Yanan Wu, Keqing He, Yuanmeng Yan, QiXiang Gao, Zhiyuan Zeng, Fujia Zheng, Lulu Zhao, Huixing Jiang, Wei Wu, Weiran Xu
Publikováno v:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b934b55c5867932b81a03a378ab214bf
https://doi.org/10.18653/v1/2022.naacl-main.307
https://doi.org/10.18653/v1/2022.naacl-main.307
Publikováno v:
Advances in Knowledge Discovery and Data Mining ISBN: 9783031059803
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7ed6ecfc2de8a361184362c404d8a9e7
https://doi.org/10.1007/978-3-031-05981-0_18
https://doi.org/10.1007/978-3-031-05981-0_18
Publikováno v:
ICASSP
Traditional document summarization models cannot handle dialogue summarization tasks perfectly. In situations with multiple speakers and complex personal pronouns referential relationships in the conversation. The predicted summaries of these models
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ff7650e72356ec95cbe211d3d894c912
https://doi.org/10.1109/icassp39728.2021.9414547
https://doi.org/10.1109/icassp39728.2021.9414547
Publikováno v:
ICASSP
Identifying intentions from users can help improve the response quality of task-oriented dialogue systems. How to use only limited labeled in-domain (ID) examples for zero-shot unknown intent detection and few-shot ID classification is a more challen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9a917ae2dd5c4d8d301b1c67d7088a2d
https://doi.org/10.1109/icassp39728.2021.9414548
https://doi.org/10.1109/icassp39728.2021.9414548
Publikováno v:
ICASSP
Detecting out-of-domain (OOD) intents is critical in a task-oriented dialog system. Existing methods rely heavily on extensive manually labeled OOD samples and lack robustness. In this paper, we propose an efficient adversarial attack mechanism to au
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::25ef7f01975834583184fafc7bdc278b
https://doi.org/10.1109/icassp39728.2021.9413908
https://doi.org/10.1109/icassp39728.2021.9413908
Autor:
Zijun Liu, Hong Xu, Zhiyuan Zeng, Yanan Wu, Weiran Xu, Huixing Jiang, Keqing He, Yuanmeng Yan
Publikováno v:
ACL/IJCNLP (2)
Detecting Out-of-Domain (OOD) or unknown intents from user queries is essential in a task-oriented dialog system. A key challenge of OOD detection is to learn discriminative semantic features. Traditional cross-entropy loss only focuses on whether a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::93c1c84ae827f9f087e7096175e92e3b
http://arxiv.org/abs/2105.14289
http://arxiv.org/abs/2105.14289
Publikováno v:
ACL/IJCNLP (1)
Learning high-quality sentence representations benefits a wide range of natural language processing tasks. Though BERT-based pre-trained language models achieve high performance on many downstream tasks, the native derived sentence representations ar
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a64f46dd9c77059a03b98d23cb0d80aa
http://arxiv.org/abs/2105.11741
http://arxiv.org/abs/2105.11741
Publikováno v:
Findings of the Association for Computational Linguistics: EMNLP 2021.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1c3af1e50d8383f8b67988bf7fcbb6ed
https://doi.org/10.18653/v1/2021.findings-emnlp.117
https://doi.org/10.18653/v1/2021.findings-emnlp.117