Abstract
In the present paper, we conduct a comparative evaluation of a multitude of information-seeking domains, using two well-known but fundamentally different algorithms for policy learning: GP-SARSA and DQN. Our goal is to gain an understanding of how the nature of such domains influences performance. Our results indicate several main domain characteristics that play an important role in policy learning performance in terms of task success rates.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Gašić M, Mrkšić N, Rojas-Barahona LM, Su P-H, Ultes S, Vandyke D, Wen T-H, Young S (2016) Dialogue manager domain adaptation using gaussian process reinforcement learning. Comput Speech Lang
Cuayáhuitl H, Yu S, Williamson A, Carse J (2016) Deep reinforcement learning for multi-domain dialogue systems. arXiv preprint arXiv:1611.08675
Papangelis A, Stylianou, Y (2016) Multi-domain spoken dialogue systems using domain-independent parameterisation. In: Domain adaptation for dialogue agents
Engel Y, Mannor S, Meir R (2005) Reinforcement learning with gaussian processes. In: Proceedings of the 22nd ICML. ACM, pp 201–208
Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529–533
Remus R (2012) Domain adaptation using domain similarity- and domain complexity-based instance selection for cross-domain sentiment analysis. In: 2012 IEEE 12th international conference on data mining workshops, Dec 2012, pp 717–723
Freitas A, Sales JE, Handschuh S, Curry E (2015) How hard is this query? Measuring the semantic complexity of schema-agnostic queries. In: IWCS 2015, p 294
Grubinger M, Leung C, Clough P (2005) Linguistic estimation of topic difficulty in cross-language image retrieval. In: Workshop of the cross-language evaluation forum for European languages. Springer, pp 558–566
Sebastiani F (1994) A probabilistic terminological logic for modelling information retrieval. In: SIGIR94. Springer, pp 122–130
Bagga A, Biermann AW (1997) Analyzing the complexity of a domain with respect to an information extraction task. In: Proceedings of the tenth international conference on research on computational linguistics (ROCLING X), pp 175–194
Pollard S, Biermann AW (2000) A measure of semantic complexity for natural language systems. In: Proceedings of the NAACL SSCNLPS, Stroudsburg, PA, USA, pp 42–46
Gašić M, Breslin C, Henderson M, Kim D, Szummer M, Thomson B, Tsiakoulis P, Young S (2013) On-line policy optimisation of bayesian spoken dialogue systems via human interaction. In: 2013 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 8367–8371
Ultes S, Rojas-Barahona L, Su PH, Vandyke D, Kim D, Casanueva I, Budzianowski P, Mrkšić N, Wen TH, Gašić M, Young S (2017) Pydial: a multi-domain statistical dialogue system toolkit. In: ACL 2017 Demo, Vancouver. ACL
Schatzmann J, Young SJ (2009) The hidden agenda user simulation model. IEEE Trans Audio Speech Lang Process 17(4):733–747
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer International Publishing AG, part of Springer Nature
About this chapter
Cite this chapter
Papangelis, A., Ultes, S., Stylianou, Y. (2019). Domain Complexity and Policy Learning in Task-Oriented Dialogue Systems. In: Eskenazi, M., Devillers, L., Mariani, J. (eds) Advanced Social Interaction with Agents . Lecture Notes in Electrical Engineering, vol 510. Springer, Cham. https://doi.org/10.1007/978-3-319-92108-2_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-92108-2_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-92107-5
Online ISBN: 978-3-319-92108-2
eBook Packages: EngineeringEngineering (R0)