Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Cho, Eunjoon"'
Autor:
Lin, Zhaojiang, Liu, Bing, Madotto, Andrea, Moon, Seungwhan, Crook, Paul, Zhou, Zhenpeng, Wang, Zhiguang, Yu, Zhou, Cho, Eunjoon, Subba, Rajen, Fung, Pascale
Zero-shot transfer learning for dialogue state tracking (DST) enables us to handle a variety of task-oriented dialogue domains without the expense of collecting in-domain data. In this work, we propose to transfer the \textit{cross-task} knowledge fr
Externí odkaz:
http://arxiv.org/abs/2109.04655
Autor:
Lin, Zhaojiang, Liu, Bing, Moon, Seungwhan, Crook, Paul, Zhou, Zhenpeng, Wang, Zhiguang, Yu, Zhou, Madotto, Andrea, Cho, Eunjoon, Subba, Rajen
Zero-shot cross-domain dialogue state tracking (DST) enables us to handle task-oriented dialogue in unseen domains without the expense of collecting in-domain data. In this paper, we propose a slot description enhanced generative approach for zero-sh
Externí odkaz:
http://arxiv.org/abs/2105.04222
Autor:
Madotto, Andrea, Lin, Zhaojiang, Zhou, Zhenpeng, Moon, Seungwhan, Crook, Paul, Liu, Bing, Yu, Zhou, Cho, Eunjoon, Wang, Zhiguang
Continual learning in task-oriented dialogue systems can allow us to add new domains and functionalities through time without incurring the high cost of a whole system retraining. In this paper, we propose a continual learning benchmark for task-orie
Externí odkaz:
http://arxiv.org/abs/2012.15504
Autor:
Sun, Kai, Moon, Seungwhan, Crook, Paul, Roller, Stephen, Silvert, Becka, Liu, Bing, Wang, Zhiguang, Liu, Honglei, Cho, Eunjoon, Cardie, Claire
Existing dialogue corpora and models are typically designed under two disjoint motives: while task-oriented systems focus on achieving functional goals (e.g., booking hotels), open-domain chatbots aim at making socially engaging conversations. In thi
Externí odkaz:
http://arxiv.org/abs/2010.12757
Autor:
Moon, Seungwhan, Kottur, Satwik, Crook, Paul A., De, Ankita, Poddar, Shivani, Levin, Theodore, Whitney, David, Difranco, Daniel, Beirami, Ahmad, Cho, Eunjoon, Subba, Rajen, Geramifard, Alborz
Next generation virtual assistants are envisioned to handle multimodal inputs (e.g., vision, memories of previous interactions, in addition to the user's utterances), and perform multimodal actions (e.g., displaying a route in addition to generating
Externí odkaz:
http://arxiv.org/abs/2006.01460
Distortion of the underlying speech is a common problem for single-channel speech enhancement algorithms, and hinders such methods from being used more extensively. A dictionary based speech enhancement method that emphasizes preserving the underlyin
Externí odkaz:
http://arxiv.org/abs/1605.01329
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
2012 IEEE International Conference on Acoustics, Speech & Signal Processing (ICASSP); 1/ 1/2012, p4569-4572, 4p
Publikováno v:
Proceedings of the 17th ACM SIGKDD International Conference: Knowledge Discovery & Data Mining; 8/21/2011, p1082-1090, 9p
Publikováno v:
Proceedings of the 7th ACM Conference: Embedded Networked Sensor Systems; 11/ 4/2009, p387-388, 2p