Adversarial Domain Adaptation for Variational Neural Language Generation in Dialogue Systems

By Van-Khanh Tran, Le-Minh Nguyen. 2018

22 citations recorded by the source corpus.

Domain Adaptation arises when we aim at learning from source domain a model that can perform 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 effectively leverage the existing knowledge in the source domain to adapt to another related domain by using only a small amount of in-domain data.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Minlie Huang
2. Fei Mi
3. Kun Qian
4. Jiyong Zhang
5. Zhou Yu
6. Liangwei Chen
7. Boi Faltings
8. Mengjie Zhao

In Computer Vision and Pattern Recognition

1. Kun Qian
2. Jiyong Zhang
3. Zhou Yu
4. Minlie Huang
5. Boi Faltings
6. Fei Mi
7. Mengjie Zhao

Citations in the corpus

• Continual Learning for Natural Language Generation in Task-oriented Dialog Systems (2020, background): “They later designed two domain adaptation critics with an adversarial training algorithm (Tran and Nguyen, 2018a).”
• Domain Adaptive Dialog Generation via Meta Learning (2019, background): “Recently, effective domain adaptation has been introduced for natural language generation in dialog systems (Tran and Nguyen, 2018; Wen et al., 2016).”
• Meta-Learning for Low-resource Natural Language Generation in Task-oriented Dialogue Systems (2019, methodology): “They later designed two domain adaptation critics with an adversarial training algo-rithm [Tran and Nguyen, 2018a] to learn an indistinguishable latent representation of the source and the target domain to better generalize to the target domain.”