Neural Response Generation with Meta-Words
arXiv:1906.06050
Abstract
We present open domain response generation with meta-words. A meta-word is a structured record that describes various attributes of a response, and thus allows us to explicitly model the one-to-many relationship within open domain dialogues and perform response generation in an explainable and controllable manner. To incorporate meta-words into generation, we enhance the sequence-to-sequence architecture with a goal tracking memory network that formalizes meta-word expression as a goal and manages the generation process to achieve the goal with a state memory panel and a state controller. Experimental results on two large-scale datasets indicate that our model can significantly outperform several state-of-the-art generation models in terms of response relevance, response diversity, accuracy of one-to-many modeling, accuracy of meta-word expression, and human evaluation.
ACL 2019
References in corpus (6)
- Sequence to Sequence Learning with Neural Networks
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- ADADELTA: An Adaptive Learning Rate Method
- Hierarchical Recurrent Attention Network for Response Generation
- Neural Response Generation with Dynamic Vocabularies
- What makes a good conversation? How controllable attributes affect human judgments