APRIL : Interactively Learning to Summarise by Combining Active Preference Learning and Reinforcement Learning. / Gao, Yang; Meyer, Christian M.; Gurevych, Iryna.
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Brussels, Belgium : Association for Computational Linguistics, 2018. p. 4120-4130.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
APRIL : Interactively Learning to Summarise by Combining Active Preference Learning and Reinforcement Learning. / Gao, Yang; Meyer, Christian M.; Gurevych, Iryna.
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Brussels, Belgium : Association for Computational Linguistics, 2018. p. 4120-4130.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - APRIL
T2 - Interactively Learning to Summarise by Combining Active Preference Learning and Reinforcement Learning
AU - Gao, Yang
AU - Meyer, Christian M.
AU - Gurevych, Iryna
PY - 2018/10/31
Y1 - 2018/10/31
N2 - We propose a method to perform automatic document summarisation without using reference summaries. Instead, our method interactively learns from users’ preferences. The merit of preference-based interactive summarisation is that preferences are easier for users to provide than reference summaries. Existing preference-based interactive learning methods suffer from high sample complexity, i.e. they need to interact with the oracle for many rounds in order to converge. In this work, we propose a new objective function, which enables us to leverage active learning, preference learning and reinforcement learning techniques in order to reduce the sample complexity. Both simulation and real-user experiments suggest that our method significantly advances the state of the art. Our source code is freely available at https://github.com/UKPLab/emnlp2018-april.
AB - We propose a method to perform automatic document summarisation without using reference summaries. Instead, our method interactively learns from users’ preferences. The merit of preference-based interactive summarisation is that preferences are easier for users to provide than reference summaries. Existing preference-based interactive learning methods suffer from high sample complexity, i.e. they need to interact with the oracle for many rounds in order to converge. In this work, we propose a new objective function, which enables us to leverage active learning, preference learning and reinforcement learning techniques in order to reduce the sample complexity. Both simulation and real-user experiments suggest that our method significantly advances the state of the art. Our source code is freely available at https://github.com/UKPLab/emnlp2018-april.
U2 - 10.18653/v1/D18-1445
DO - 10.18653/v1/D18-1445
M3 - Conference contribution
SP - 4120
EP - 4130
BT - Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
PB - Association for Computational Linguistics
CY - Brussels, Belgium
ER -