Diversifying Dialogue Generation with Non-Conversational Text
arXiv:2005.04346
Abstract
Neural network-based sequence-to-sequence (seq2seq) models strongly suffer from the low-diversity problem when it comes to open-domain dialogue generation. As bland and generic utterances usually dominate the frequency distribution in our daily chitchat, avoiding them to generate more interesting responses requires complex data filtering, sampling techniques or modifying the training objective. In this paper, we propose a new perspective to diversify dialogue generation by leveraging non-conversational text. Compared with bilateral conversations, non-conversational text are easier to obtain, more diverse and cover a much broader range of topics. We collect a large-scale non-conversational corpus from multi sources including forum comments, idioms and book snippets. We further present a training paradigm to effectively incorporate these text via iterative back translation. The resulting model is tested on two conversational datasets and is shown to produce significantly more diverse responses without sacrificing the relevance with context.
arXiv commentAccepted to ACL 2020 (long)
References in corpus (12)
- A Neural Conversational Model
- The Curious Case of Neural Text Degeneration
- Deep Reinforcement Learning for Dialogue Generation
- A Simple, Fast Diverse Decoding Algorithm for Neural Generation
- A Deep Reinforcement Learning Chatbot
- Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization
- A Persona-Based Neural Conversation Model
- Discriminability objective for training descriptive captions
- Unsupervised Pidgin Text Generation By Pivoting English Data and Self-Training
- Improving Multi-turn Dialogue Modelling with Utterance ReWriter
- Explaining and Generalizing Back-Translation through Wake-Sleep
- Select and Attend: Towards Controllable Content Selection in Text Generation