Dialogue Strategy Adaptation to New Action Sets Using Multi-dimensional
Modelling
- URL: http://arxiv.org/abs/2204.07082v1
- Date: Thu, 14 Apr 2022 16:26:22 GMT
- Title: Dialogue Strategy Adaptation to New Action Sets Using Multi-dimensional
Modelling
- Authors: Simon Keizer, Norbert Braunschweiler, Svetlana Stoyanchev, Rama
Doddipatla
- Abstract summary: A major bottleneck for building statistical spoken dialogue systems is the need for large amounts of training data.
We adopt the multi-dimensional approach to dialogue management and evaluate its potential for transfer learning.
Specifically, we exploit pre-trained task-independent policies to speed up training for an extended task-specific action set.
- Score: 15.575400480417844
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: A major bottleneck for building statistical spoken dialogue systems for new
domains and applications is the need for large amounts of training data. To
address this problem, we adopt the multi-dimensional approach to dialogue
management and evaluate its potential for transfer learning. Specifically, we
exploit pre-trained task-independent policies to speed up training for an
extended task-specific action set, in which the single summary action for
requesting a slot is replaced by multiple slot-specific request actions. Policy
optimisation and evaluation experiments using an agenda-based user simulator
show that with limited training data, much better performance levels can be
achieved when using the proposed multi-dimensional adaptation method. We
confirm this improvement in a crowd-sourced human user evaluation of our spoken
dialogue system, comparing partially trained policies. The multi-dimensional
system (with adaptation on limited training data in the target scenario)
outperforms the one-dimensional baseline (without adaptation on the same amount
of training data) by 7% perceived success rate.
Related papers
- Towards All-in-one Pre-training via Maximizing Multi-modal Mutual
Information [77.80071279597665]
We propose an all-in-one single-stage pre-training approach, named Maximizing Multi-modal Mutual Information Pre-training (M3I Pre-training)
Our approach achieves better performance than previous pre-training methods on various vision benchmarks, including ImageNet classification, object detection, LVIS long-tailed object detection, and ADE20k semantic segmentation.
arXiv Detail & Related papers (2022-11-17T18:59:49Z) - An Information-Theoretic Approach for Estimating Scenario Generalization
in Crowd Motion Prediction [27.10815774845461]
We propose a novel scoring method, which characterizes generalization of models trained on source crowd scenarios and applied to target crowd scenarios.
The Interaction component aims to characterize the difficulty of scenario domains, while the diversity of a scenario domain is captured in the Diversity score.
Our experimental results validate the efficacy of the proposed method on several simulated and real-world (source,target) generalization tasks.
arXiv Detail & Related papers (2022-11-02T01:39:30Z) - Is MultiWOZ a Solved Task? An Interactive TOD Evaluation Framework with
User Simulator [37.590563896382456]
We propose an interactive evaluation framework for Task-Oriented Dialogue (TOD) systems.
We first build a goal-oriented user simulator based on pre-trained models and then use the user simulator to interact with the dialogue system to generate dialogues.
Experimental results show that RL-based TOD systems trained by our proposed user simulator can achieve nearly 98% inform and success rates.
arXiv Detail & Related papers (2022-10-26T07:41:32Z) - Effective Adaptation in Multi-Task Co-Training for Unified Autonomous
Driving [103.745551954983]
In this paper, we investigate the transfer performance of various types of self-supervised methods, including MoCo and SimCLR, on three downstream tasks.
We find that their performances are sub-optimal or even lag far behind the single-task baseline.
We propose a simple yet effective pretrain-adapt-finetune paradigm for general multi-task training.
arXiv Detail & Related papers (2022-09-19T12:15:31Z) - Reinforcement Learning of Multi-Domain Dialog Policies Via Action
Embeddings [38.51601073819774]
Learning task-oriented dialog policies via reinforcement learning typically requires large amounts of interaction with users.
We propose to leverage data from across different dialog domains, thereby reducing the amount of data required from each given domain.
We show how this approach is capable of learning with significantly less interaction with users, with a reduction of 35% in the number of dialogs required to learn, and to a higher level of proficiency than training separate policies for each domain on a set of simulated domains.
arXiv Detail & Related papers (2022-07-01T14:49:05Z) - Self-training Improves Pre-training for Few-shot Learning in
Task-oriented Dialog Systems [47.937191088981436]
Large-scale pre-trained language models, have shown promising results for few-shot learning in ToD.
We propose a self-training approach that iteratively labels the most confident unlabeled data to train a stronger Student model.
We conduct experiments and present analyses on four downstream tasks in ToD, including intent classification, dialog state tracking, dialog act prediction, and response selection.
arXiv Detail & Related papers (2021-08-28T07:22:06Z) - High-Quality Diversification for Task-Oriented Dialogue Systems [18.455916009255485]
Training DRL agents with diverse dialogue trajectories prepare them well for rare user requests and unseen situations.
One effective diversification method is to let the agent interact with a diverse set of learned user models.
We propose a novel dialogue diversification method for task-oriented dialogue systems trained in simulators.
arXiv Detail & Related papers (2021-06-02T02:10:07Z) - Meta Dialogue Policy Learning [58.045067703675095]
We propose Deep Transferable Q-Network (DTQN) to utilize shareable low-level signals between domains.
We decompose the state and action representation space into feature subspaces corresponding to these low-level components.
In experiments, our model outperforms baseline models in terms of both success rate and dialogue efficiency.
arXiv Detail & Related papers (2020-06-03T23:53:06Z) - Guided Dialog Policy Learning without Adversarial Learning in the Loop [103.20723982440788]
A number of adversarial learning methods have been proposed to learn the reward function together with the dialogue policy.
We propose to decompose the adversarial training into two steps.
First, we train the discriminator with an auxiliary dialogue generator and then incorporate a derived reward model into a common RL method to guide the dialogue policy learning.
arXiv Detail & Related papers (2020-04-07T11:03:17Z) - Hybrid Generative-Retrieval Transformers for Dialogue Domain Adaptation [77.62366712130196]
We present the winning entry at the fast domain adaptation task of DSTC8, a hybrid generative-retrieval model based on GPT-2 fine-tuned to the multi-domain MetaLWOz dataset.
Our model uses retrieval logic as a fallback, being SoTA on MetaLWOz in human evaluation (>4% improvement over the 2nd place system) and attaining competitive generalization performance in adaptation to the unseen MultiWOZ dataset.
arXiv Detail & Related papers (2020-03-03T18:07:42Z)
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.