Variational Transformers for Diverse Response Generation
arXiv:2003.12738
Abstract
Despite the great promise of Transformers in many sequence modeling tasks (e.g., machine translation), their deterministic nature hinders them from generalizing to high entropy tasks such as dialogue response generation. Previous work proposes to capture the variability of dialogue responses with a recurrent neural network (RNN)-based conditional variational autoencoder (CVAE). However, the autoregressive computation of the RNN limits the training efficiency. Therefore, we propose the Variational Transformer (VT), a variational self-attentive feed-forward sequence model. The VT combines the parallelizability and global receptive field of the Transformer with the variational nature of the CVAE by incorporating stochastic latent variables into Transformers. We explore two types of the VT: 1) modeling the discourse-level diversity with a global latent variable; and 2) augmenting the Transformer decoder with a sequence of fine-grained latent variables. Then, the proposed models are evaluated on three conversational datasets with both automatic metric and human evaluation. The experimental results show that our models improve standard Transformers and other baselines in terms of diversity, semantic relevance, and human judgment.
open domain dialogue
References in corpus (3)
Cited by in corpus (6)
- Fast Parallel Hypertree Decompositions in Logarithmic Recursion Depth
- Transformer-based Conditional Variational Autoencoder for Controllable Story Generation
- Constructing Emotion Consensus and Utilizing Unpaired Data for Empathetic Dialogue Generation
- Variational Prefix Tuning for Diverse and Accurate Code Summarization Using Pre-trained Language Models
- WakaVT: A Sequential Variational Transformer for Waka Generation
- Identifying Untrustworthy Samples: Data Filtering for Open-domain Dialogues with Bayesian Optimization