Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention
Semantically controlled neural response generation on limited-domain has achieved great performance. However, moving towards multi-domain large-scale scenarios are shown to be difficult because the possible combinations of semantic inputs grow exponentially with the number of domains. To alleviate such scalability issue, we exploit the structure of dialog acts to build a multi-layer hierarchical graph, where each act is represented as a root-to-leaf route on the graph. Then, we incorporate such graph structure prior as an inductive bias to build a hierarchical disentangled self-attention network, where we disentangle attention heads to model designated nodes on the dialog act graph. By activating different (disentangled) heads at each layer, combinatorially many dialog act semantics can be modeled to control the neural response generation. On the large-scale Multi-Domain-WOZ dataset, our model can yield a significant improvement over the baselines on various automatic and human evaluation metrics.
Code (2)
Tasks
Data-to-Text GenerationInductive BiasResponse GenerationSimilar Papers 제목 키워드 기반
Retrieval-based Goal-Oriented Dialogue Generation
Most research on dialogue has focused either on dialogue generation for openended chit chat or on state tracking for goal-directed dialogue. In this work, we explore a hybrid approach to goal-oriented dialogue generation…
DecoderDialogue GenerationRetrievalMulti-task Learning for Natural Language Generation in Task-Oriented Dialogue
In task-oriented dialogues, Natural Language Generation (NLG) is the final yet crucial step to produce user-facing system utterances. The result of NLG is directly related to the perceived quality and usability of a dial…
Language ModelingLanguage ModellingMulti-Task LearningText GenerationMulti-turn Dialogue Response Generation in an Adversarial Learning Framework
We propose an adversarial learning approach for generating multi-turn dialogue responses. Our proposed framework, hredGAN, is based on conditional generative adversarial networks (GANs). The GAN's generator is a modified…
DecoderResponse GenerationWord EmbeddingsA Simple and Efficient Multi-Task Learning Approach for Conditioned Dialogue Generation
Conditioned dialogue generation suffers from the scarcity of labeled responses. In this work, we exploit labeled non-dialogue text data related to the condition, which are much easier to collect. We propose a multi-task …
Dialogue GenerationLanguage ModellingMulti-Task LearningText GenerationAn Adversarial Approach to High-Quality, Sentiment-Controlled Neural Dialogue Generation
In this work, we propose a method for neural dialogue response generation that allows not only generating semantically reasonable responses according to the dialogue history, but also explicitly controlling the sentiment…
Dialogue GenerationResponse GenerationVocal Bursts Intensity Prediction