Meta-Reinforced Multi-Domain State Generator for Dialogue Systems

2020-07-01 · ACL 2020 6 · Yi Huang, Junlan Feng, Min Hu, Xiaoting Wu, Xiaoyu Du, Shuo Ma

A Dialogue State Tracker (DST) is a core component of a modular task-oriented dialogue system. Tremendous progress has been made in recent years. However, the major challenges remain. The state-of-the-art accuracy for DST is below 50{\%} for a multi-domain dialogue task. A learnable DST for any new domain requires a large amount of labeled in-domain data and training from scratch. In this paper, we propose a Meta-Reinforced Multi-Domain State Generator (MERET). Our first contribution is to improve the DST accuracy. We enhance a neural model based DST generator with a reward manager, which is built on policy gradient reinforcement learning (RL) to fine-tune the generator. With this change, we are able to improve the joint accuracy of DST from 48.79{\%} to 50.91{\%} on the MultiWOZ corpus. Second, we explore to train a DST meta-learning model with a few domains as source domains and a new domain as target domain. We apply the model-agnostic meta-learning algorithm (MAML) to DST and the obtained meta-learning model is used for new domain adaptation. Our experimental results show this solution is able to outperform the traditional training approach with extremely less training data in target domain.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Adaptation Meta-Learning Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

DST Dynamic sparse training methods train neural networks in a sparse manner, starting with an initial sparse mask, and periodically updating the mask based on some criteria.

Reinforced Information Retrieval

2025-02-17 · Chaofan Li, Zheng Liu, Jianlyv Chen, Defu Lian 외

While retrieval techniques are widely used in practice, they still face significant challenges in cross-domain scenarios. Recently, generation-augmented methods have emerged as a promising solution to this problem. These…

Domain Adaptation Information Retrieval Retrieval

Meta-Reinforced Synthetic Data for One-Shot Fine-Grained Visual Recognition

2019-11-17 · NeurIPS 2019 12 · Satoshi Tsutsui, Yanwei Fu, David Crandall

One-shot fine-grained visual recognition often suffers from the problem of training data scarcity for new fine-grained classes. To alleviate this problem, an off-the-shelf image generator can be applied to synthesize add…

Fine-Grained Image Classification Fine-Grained Visual Recognition image-classification Image Classification+2

Selective Transfer with Reinforced Transfer Network for Partial Domain Adaptation

2019-05-26 · CVPR 2020 6 · Zhihong Chen, Chao Chen, Zhaowei Cheng, Boyuan Jiang 외

One crucial aspect of partial domain adaptation (PDA) is how to select the relevant source samples in the shared classes for knowledge transfer. Previous PDA methods tackle this problem by re-weighting the source samples…

Domain Adaptation Partial Domain Adaptation Reinforcement Learning Reinforcement Learning (RL)+1

MobileCLIP2: Improving Multi-Modal Reinforced Training

2025-08-28 · Fartash Faghri, Pavan Kumar Anasosalu Vasu, Cem Koc, Vaishaal Shankar 외 arxiv

Foundation image-text models such as CLIP with zero-shot capabilities enable a wide array of applications. MobileCLIP is a recent family of image-text models at 3-15ms latency and 50-150M parameters with state-of-the-art…

Knowledge Distillation

Meta Fine-Tuning Neural Language Models for Multi-Domain Text Mining

2020-03-29 · EMNLP 2020 11 · Chengyu Wang, Minghui Qiu, Jun Huang, Xiaofeng He

Pre-trained neural language models bring significant improvement for various NLP tasks, by fine-tuning the models on task-specific training sets. During fine-tuning, the parameters are initialized from pre-trained models…

Few-Shot Learning Language Modeling Language Modelling