mlsanityData to 13 Oct 2026

Findings from Experiments of On-line Joint Reinforcement Learning of Semantic Parser and Dialogue Manager with real Users

arXiv 2110.13213 ↗First posted 25 Oct 2021cs.CL cs.HCcited by 0

Not on the map. Why?

Abstract (arXiv)

Design of dialogue systems has witnessed many advances lately, yet acquiring huge set of data remains an hindrance to their fast development for a new task or language. Besides, training interactive systems with batch data is not satisfactory. On-line learning is pursued in this paper as a convenient way to alleviate these difficulties. After the system modules are initiated, a single process handles data collection, annotation and use in training algorithms. A new challenge is to control the cost of the on-line learning borne by the user. Our work focuses on learning the semantic parsing and dialogue management modules (speech recognition and synthesis offer ready-for-use solutions). In this context we investigate several variants of simultaneous learning which are tested in user trials. In our experiments, with varying merits, they can all achieve good performance with only a few hundreds of training dialogues and overstep a handcrafted system. The analysis of these experiments gives us some insights, discussed in the paper, into the difficulty for the system's trainers to establish a coherent and constant behavioural strategy to enable a fast and good-quality training phase.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 22 of its 58 references that are in the map. First posted on arXiv 25 Oct 2021.

Builds on

22 of 58 references.

References · 22

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,304
  2. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,360
  3. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 761
  4. 2016A Network-based End-to-End Trainable Task-oriented Dialogue Systemcited by 252
  5. 2019TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agentscited by 188
  6. 2019FlauBERT: Unsupervised Language Model Pre-training for Frenchcited by 153
  7. 2019Learning from Dialogue after Deployment: Feed Yourself, Chatbot!cited by 102
  8. 2019Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Modelscited by 53
  9. 2017End-to-End Task-Completion Neural Dialogue Systemscited by 52
  10. 2016Dialogue Learning With Human-In-The-Loopcited by 46
  11. 2017Towards Zero-Shot Frame Semantic Parsing for Domain Scalingcited by 40
  12. 2016Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Accesscited by 36
10 more
  1. 2016On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systemscited by 28
  2. 2018Zero-Shot Dialog Generation with Cross-Domain Latent Actionscited by 23
  3. 2017Latent Intention Dialogue Modelscited by 15
  4. 2018Multi-task learning for Joint Language Understanding and Dialogue State Trackingcited by 15
  5. 2014Kalman Temporal Differencescited by 10
  6. 2017A Benchmarking Environment for Reinforcement Learning Based Task Oriented Dialogue Managementcited by 8
  7. 2016End-to-End Joint Learning of Natural Language Understanding and Dialogue Managercited by 6
  8. 2019Jointly Learning Semantic Parser and Natural Language Generator via Dual Information Maximizationcited by 6
  9. 2013Zero-Shot Learning for Semantic Utterance Classificationcited by 5
  10. 2018Nearly Zero-Shot Learning for Semantic Decoding in Spoken Dialogue Systemscited by 1

Built on by

Not cited yet.