Zobrazeno 1 - 10
of 36
pro vyhledávání: '"Baolin Peng"'
Autor:
Srinivas Sunkara, Luis A. Lastras, Jonathan K. Kummerfeld, Hannes Schulz, Walter S. Lasecki, Anoop Cherian, Adam Atkinson, Seokhwan Kim, Chiori Hori, Xiaoxue Zang, Jinchao Li, Sungjin Lee, Minlie Huang, R. Chulaka Gunasekara, Michel Galley, Tim K. Marks, Raghav Gupta, Mahmoud Adada, Baolin Peng, Abhinav Rastogi, Jianfeng Gao
Publikováno v:
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 29:2529-2540
This paper introduces the Eighth Dialog System Technology Challenge. In line with recent challenges, the eighth edition focuses on applying end-to-end dialog technologies in a pragmatic way for multi-domain task-completion, noetic response selection,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8d8fa80d824fc445e0d86d2a58bd61c5
https://doi.org/10.1109/taslp.2021.3078368
https://doi.org/10.1109/taslp.2021.3078368
Publikováno v:
Transactions of the Association for Computational Linguistics. 9:807-824
We present a new method, Soloist,1 that uses transfer learning and machine teaching to build task bots at scale. We parameterize classical modular task-oriented dialog systems using a Transformer-based auto-regressive language model, which subsumes d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1e278a9ca01ea7685cbef316ba4d8c2a
https://doi.org/10.1162/tacl_a_00399
https://doi.org/10.1162/tacl_a_00399
Knowledge-grounded dialogue systems are challenging to build due to the lack of training data and heterogeneous knowledge sources. Existing systems perform poorly on unseen topics due to limited topics covered in the training data. In addition, heter
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a72ed713c5cb3680d691a9a27b261bfd
http://arxiv.org/abs/2112.07924
http://arxiv.org/abs/2112.07924
Building a socially intelligent agent involves many challenges, one of which is to teach the agent to speak guided by its value like a human. However, value-driven chatbots are still understudied in the area of dialogue systems. Most existing dataset
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::73cc44e397eba44143949471169fbf13
http://arxiv.org/abs/2112.06346
http://arxiv.org/abs/2112.06346
Publikováno v:
Interspeech 2021.
The training of spoken language understanding (SLU) models often faces the problem of data scarcity. In this paper, we put forward a data augmentation method using pretrained language models to boost the variability and accuracy of generated utteranc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dd73265d34c6aa2b28eda39e4cf928d1
https://doi.org/10.21437/interspeech.2021-117
https://doi.org/10.21437/interspeech.2021-117
Autor:
Jiaxin Huang, Chunyuan Li, Krishan Subudhi, Damien Jose, Shobana Balakrishnan, Weizhu Chen, Baolin Peng, Jianfeng Gao, Jiawei Han
Publikováno v:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::771f871b722539aa284f5c988684b81f
https://doi.org/10.18653/v1/2021.emnlp-main.813
https://doi.org/10.18653/v1/2021.emnlp-main.813
Autor:
Song-Chun Zhu, Liang Qiu, Pan Lu, Yuan Liang, Zhou Yu, Baolin Peng, Ying Nian Wu, Yizhou Zhao
Publikováno v:
ACL/IJCNLP (1)
Inferring social relations from dialogues is vital for building emotionally intelligent robots to interpret human language better and act accordingly. We model the social network as an And-or Graph, named SocAoG, for the consistency of relations amon
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::454d7559a7a3230b0d6cf97e190b8be0
https://doi.org/10.18653/v1/2021.acl-long.54
https://doi.org/10.18653/v1/2021.acl-long.54
Publikováno v:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9bb7b7acf5a53113755b4b0638cc8316
https://doi.org/10.18653/v1/2021.emnlp-main.616
https://doi.org/10.18653/v1/2021.emnlp-main.616
Publikováno v:
ACL/IJCNLP (1)
This paper presents a novel task to generate poll questions for social media posts. It offers an easy way to hear the voice from the public and learn from their feelings to important social topics. While most related work tackles formal languages (e.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::33a59ccce5af8abfecc6ff1000a02a6c
https://doi.org/10.18653/v1/2021.acl-long.3
https://doi.org/10.18653/v1/2021.acl-long.3
Autor:
Jianfeng Gao, Baolin Peng, Qi Zhu, Jinchao Li, Xiang Li, Ryuichi Takanobu, Xiaoyan Zhu, Minlie Huang, Yan Fang, Zheng Zhang
Publikováno v:
ACL (demo)
We present ConvLab-2, an open-source toolkit that enables researchers to build task-oriented dialogue systems with state-of-the-art models, perform an end-to-end evaluation, and diagnose the weakness of systems. As the successor of ConvLab (Lee et al
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8254cca606c81fd29c7a4400a96b910e
http://arxiv.org/abs/2002.04793
http://arxiv.org/abs/2002.04793