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

• URL: http://arxiv.org/abs/2110.13213v1
• Date: Mon, 25 Oct 2021 18:51:41 GMT
• Title: Findings from Experiments of On-line Joint Reinforcement Learning of Semantic Parser and Dialogue Manager with real Users
• Authors: Matthieu Riou and Bassam Jabaian and St\'ephane Huet and Fabrice Lef\`evre
• Abstract summary: On-line learning is pursued in this paper as a convenient way to alleviate these difficulties. A new challenge is to control the cost of the on-line learning borne by the user.
• Score: 3.9686445409447617
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Pre-training Multi-party Dialogue Models with Latent Discourse Inference [85.9683181507206]
  We pre-train a model that understands the discourse structure of multi-party dialogues, namely, to whom each utterance is replying. To fully utilize the unlabeled data, we propose to treat the discourse structures as latent variables, then jointly infer them and pre-train the discourse-aware model.
  arXiv  Detail & Related papers  (2023-05-24T14:06:27Z)
• Multi-Task Learning based Online Dialogic Instruction Detection with Pre-trained Language Models [34.66425105076059]
  We propose a multi-task paradigm which enhances the ability to distinguish instances of different classes by enlarging the margin between categories via contrastive loss. Experiments on a real-world online educational data set demonstrate that our approach achieves superior performance compared to representative baselines.
  arXiv  Detail & Related papers  (2021-07-15T04:57:57Z)
• Alexa Conversations: An Extensible Data-driven Approach for Building Task-oriented Dialogue Systems [21.98135285833616]
  Traditional goal-oriented dialogue systems rely on various components such as natural language understanding, dialogue state tracking, policy learning and response generation. We present a new approach for building goal-oriented dialogue systems that is scalable, as well as data efficient.
  arXiv  Detail & Related papers  (2021-04-19T07:09:27Z)
• Continual Learning in Task-Oriented Dialogue Systems [49.35627673523519]
  Continual learning in task-oriented dialogue systems can allow us to add new domains and functionalities through time without incurring the high cost of a whole system retraining. We propose a continual learning benchmark for task-oriented dialogue systems with 37 domains to be learned continuously in four settings.
  arXiv  Detail & Related papers  (2020-12-31T08:44:25Z)
• Learning Adaptive Language Interfaces through Decomposition [89.21937539950966]
  We introduce a neural semantic parsing system that learns new high-level abstractions through decomposition. Users interactively teach the system by breaking down high-level utterances describing novel behavior into low-level steps.
  arXiv  Detail & Related papers  (2020-10-11T08:27:07Z)
• MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems [75.43457658815943]
  We propose Minimalist Transfer Learning (MinTL) to simplify the system design process of task-oriented dialogue systems. MinTL is a simple yet effective transfer learning framework, which allows us to plug-and-play pre-trained seq2seq models. We instantiate our learning framework with two pre-trained backbones: T5 and BART, and evaluate them on MultiWOZ.
  arXiv  Detail & Related papers  (2020-09-25T02:19:13Z)
• Rethinking Supervised Learning and Reinforcement Learning in Task-Oriented Dialogue Systems [58.724629408229205]
  We demonstrate how traditional supervised learning and a simulator-free adversarial learning method can be used to achieve performance comparable to state-of-the-art RL-based methods. Our main goal is not to beat reinforcement learning with supervised learning, but to demonstrate the value of rethinking the role of reinforcement learning and supervised learning in optimizing task-oriented dialogue systems.
  arXiv  Detail & Related papers  (2020-09-21T12:04:18Z)
• A System for Real-Time Interactive Analysis of Deep Learning Training [66.06880335222529]
  Currently available systems are limited to monitoring only the logged data that must be specified before the training process starts. We present a new system that enables users to perform interactive queries on live processes generating real-time information.
  arXiv  Detail & Related papers  (2020-01-05T11:33:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.