This week we have been at the NIPS deepRL symposium presenting the paper “A Benchmarking Environment for Reinforcement Learning Based Task Oriented Dialogue Management“. All the benchmarked tasks and RL algorithms have been released in PyDial, feel free to try them!
Paweł and Inigo will be attending NIPS 2017 in Long Beach (LA). Check out our posters at two workshops:
- A Benchmarking Environment for Reinforcement Learning Based Task Oriented Dialogue Management, Deep Reinforcement Learning Symposium (Thursday 2pm-9pm)
- Uncertainty Estimates for Efficient Neural Network-based Dialogue Policy Optimisation, Bayesian Deep Learning Workshop (Saturday 8am-6pm)
Nikola and Lina will be attending EMNLP 2017 in Copenhagen. Check out our posters:
- Semantic Specialisation of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints (Monday 10:30, 7D Poster Session)
- Cross-Lingual Induction and Transfer of Verb Classes Based on Word Vector Space Specialisation (Monday 10:30, 7D Poster Session)
Several of our members (Milica, Stefan, Eddy and Paweł) will be attending SigDial 2017 in Saarbrücken. Check out our talks and posters:
- Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management (Tuesday, talk)
- Sub-domain Modelling for Dialogue Management with Hierarchical Reinforcement Learning (Tuesday, poster)
- Reward-Balancing for Statistical Spoken Dialogue Systems using Multi-objective Reinforcement Learning (Tuesday, poster)
Several of our members (Steve, Stefan, Inigo, Eddy and Nikola) will be attending ACL 2017 in Vancouver. Check out our talks and posters:
- Neural Belief Tracker: Data-Driven Dialogue State Tracking (Tuesday Poster Session)
- Morph-fitting: Fine-Tuning Word Vector Spaces with Simple Language-Specific Rules (Monday,10:49AM, Semantics I Session).
- PyDial: A Multi-domain Statistical Dialogue System Toolkit (Tuesday Poster Session)