Semantically conditioned lstm-based natural language generation for spoken dialogue systems TH Wen, M Gasic, N Mrksic, PH Su, D Vandyke, S Young arXiv preprint arXiv:1508.01745, 2015 | 682 | 2015 |
A network-based end-to-end trainable task-oriented dialogue system TH Wen, D Vandyke, N Mrksic, M Gasic, LM Rojas-Barahona, PH Su, ... arXiv preprint arXiv:1604.04562, 2016 | 663 | 2016 |
Counter-fitting word vectors to linguistic constraints N Mrkšić, DO Séaghdha, B Thomson, M Gašić, L Rojas-Barahona, PH Su, ... arXiv preprint arXiv:1603.00892, 2016 | 247 | 2016 |
Sample-efficient actor-critic reinforcement learning with supervised data for dialogue management PH Su, P Budzianowski, S Ultes, M Gasic, S Young arXiv preprint arXiv:1707.00130, 2017 | 163* | 2017 |
Stochastic language generation in dialogue using recurrent neural networks with convolutional sentence reranking TH Wen, M Gasic, D Kim, N Mrksic, PH Su, D Vandyke, S Young arXiv preprint arXiv:1508.01755, 2015 | 157 | 2015 |
Multi-domain dialog state tracking using recurrent neural networks N Mrkšić, DO Séaghdha, B Thomson, M Gašić, PH Su, D Vandyke, ... arXiv preprint arXiv:1506.07190, 2015 | 150 | 2015 |
On-line active reward learning for policy optimisation in spoken dialogue systems PH Su, M Gasic, N Mrksic, L Rojas-Barahona, S Ultes, D Vandyke, ... arXiv preprint arXiv:1605.07669, 2016 | 133 | 2016 |
Multi-domain neural network language generation for spoken dialogue systems TH Wen, M Gasic, N Mrksic, LM Rojas-Barahona, PH Su, D Vandyke, ... arXiv preprint arXiv:1603.01232, 2016 | 131 | 2016 |
Pydial: A multi-domain statistical dialogue system toolkit S Ultes, LMR Barahona, PH Su, D Vandyke, D Kim, I Casanueva, ... Proceedings of ACL 2017, System Demonstrations, 73-78, 2017 | 113 | 2017 |
Sample-efficient actor-critic reinforcement learning with supervised data for dialogue management PH Su, P Budzianowski, S Ultes, M Gasic, S Young arXiv preprint arXiv:1707.00130, 2017 | 85 | 2017 |
Conditional generation and snapshot learning in neural dialogue systems TH Wen, M Gasic, N Mrksic, LM Rojas-Barahona, PH Su, S Ultes, ... arXiv preprint arXiv:1606.03352, 2016 | 57 | 2016 |
Learning from real users: Rating dialogue success with neural networks for reinforcement learning in spoken dialogue systems PH Su, D Vandyke, M Gasic, D Kim, N Mrksic, TH Wen, S Young INTERSPEECH, 2015 | 56 | 2015 |
Policy committee for adaptation in multi-domain spoken dialogue systems M Gašić, N Mrkšić, P Su, D Vandyke, TH Wen, S Young 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU …, 2015 | 46 | 2015 |
Sample efficient deep reinforcement learning for dialogue systems with large action spaces G Weisz, P Budzianowski, PH Su, M Gašić IEEE/ACM Transactions on Audio, Speech, and Language Processing 26 (11 …, 2018 | 41 | 2018 |
A benchmarking environment for reinforcement learning based task oriented dialogue management I Casanueva, P Budzianowski, PH Su, N Mrkšić, TH Wen, S Ultes, ... arXiv preprint arXiv:1711.11023, 2017 | 39 | 2017 |
Sub-domain modelling for dialogue management with hierarchical reinforcement learning P Budzianowski, S Ultes, PH Su, N Mrkšić, TH Wen, I Casanueva, ... arXiv preprint arXiv:1706.06210, 2017 | 38 | 2017 |
Reward shaping with recurrent neural networks for speeding up on-line policy learning in spoken dialogue systems PH Su, D Vandyke, M Gasic, N Mrksic, TH Wen, S Young arXiv preprint arXiv:1508.03391, 2015 | 38 | 2015 |
Dialogue manager domain adaptation using gaussian process reinforcement learning M Gašić, N Mrkšić, LM Rojas-Barahona, PH Su, S Ultes, D Vandyke, ... Computer Speech & Language 45, 552-569, 2017 | 34 | 2017 |
Convert: Efficient and accurate conversational representations from transformers M Henderson, I Casanueva, N Mrkšić, PH Su, TH Wen, I Vulić arXiv preprint arXiv:1911.03688, 2019 | 31 | 2019 |
Feudal reinforcement learning for dialogue management in large domains I Casanueva, P Budzianowski, PH Su, S Ultes, L Rojas-Barahona, ... arXiv preprint arXiv:1803.03232, 2018 | 28 | 2018 |