Zobrazeno 1 - 10
of 44
pro vyhledávání: '"Ryu, Seonghan"'
Autor:
Cuayáhuitl, Heriberto, Lee, Donghyeon, Ryu, Seonghan, Cho, Yongjin, Choi, Sungja, Indurthi, Satish, Yu, Seunghak, Choi, Hyungtak, Hwang, Inchul, Kim, Jihie
Trainable chatbots that exhibit fluent and human-like conversations remain a big challenge in artificial intelligence. Deep Reinforcement Learning (DRL) is promising for addressing this challenge, but its successful application remains an open questi
Externí odkaz:
http://arxiv.org/abs/1908.10422
Autor:
Cuayáhuitl, Heriberto, Lee, Donghyeon, Ryu, Seonghan, Choi, Sungja, Hwang, Inchul, Kim, Jihie
Training chatbots using the reinforcement learning paradigm is challenging due to high-dimensional states, infinite action spaces and the difficulty in specifying the reward function. We address such problems using clustered actions instead of infini
Externí odkaz:
http://arxiv.org/abs/1908.10331
The amount of dialogue history to include in a conversational agent is often underestimated and/or set in an empirical and thus possibly naive way. This suggests that principled investigations into optimal context windows are urgently needed given th
Externí odkaz:
http://arxiv.org/abs/1812.00350
To ensure satisfactory user experience, dialog systems must be able to determine whether an input sentence is in-domain (ID) or out-of-domain (OOD). We assume that only ID sentences are available as training data because collecting enough OOD sentenc
Externí odkaz:
http://arxiv.org/abs/1807.11567
The amount of dialogue history to include in a conversational agent is often underestimated and/or set in an empirical and thus possibly naive way. This suggests that principled investigations into optimal context windows are urgently needed given th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::93365bc1a8c1db15c56ec89921fc0754
http://arxiv.org/abs/1812.00350
http://arxiv.org/abs/1812.00350
Publikováno v:
In Pattern Recognition Letters 1 March 2017 88:26-32
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
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:
2015 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU); 1/1/2015, p798-805, 8p
Publikováno v:
Natural Language Dialog Systems & Intelligent Assistants; 2015, p113-118, 6p