Adversarial Domain Adaptation for Variational Neural Language Generation in Dialogue Systems
arXiv:1808.02586
Abstract
Domain Adaptation arises when we aim at learning from source domain a model that can per- form acceptably well on a different target domain. It is especially crucial for Natural Language Generation (NLG) in Spoken Dialogue Systems when there are sufficient annotated data in the source domain, but there is a limited labeled data in the target domain. How to effectively utilize as much of existing abilities from source domains is a crucial issue in domain adaptation. In this paper, we propose an adversarial training procedure to train a Variational encoder-decoder based language generator via multiple adaptation steps. In this procedure, a model is first trained on a source domain data and then fine-tuned on a small set of target domain utterances under the guidance of two proposed critics. Experimental results show that the proposed method can effec- tively leverage the existing knowledge in the source domain to adapt to another related domain by using only a small amount of in-domain data.
arXiv commentAccepted at COLING 2018, 13 pages
References in corpus (6)
- Auto-Encoding Variational Bayes
- Variational Inference with Normalizing Flows
- A Recurrent Latent Variable Model for Sequential Data
- Hierarchical Multiscale Recurrent Neural Networks
- Individual and Domain Adaptation in Sentence Planning for Dialogue
- Semantic Refinement GRU-based Neural Language Generation for Spoken Dialogue Systems
Cited by in corpus (5)
- Domain Adaptive Dialog Generation via Meta Learning
- Template Guided Text Generation for Task-Oriented Dialogue
- Continual Learning for Natural Language Generation in Task-oriented Dialog Systems
- Schema-Guided Natural Language Generation
- Tree-Structured Semantic Encoder with Knowledge Sharing for Domain Adaptation in Natural Language Generation