Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints

Abstract

Neural conversation models tend to generate safe, generic responses for most inputs. This is due to the limitations of likelihood-based decoding objectives in generation tasks with diverse outputs, such as conversation. To address this challenge, we propose a simple yet effective approach for incorporating side information in the form of distributional constraints over the generated responses. We propose two constraints that help generate more content rich responses that are based on a model of syntax and topics (Griffiths et al., 2005) and semantic similarity (Arora et al., 2016). We evaluate our approach against a variety of competitive baselines, using both automatic metrics and human judgments, showing that our proposed approach generates responses that are much less generic without sacrificing plausibility. A working demo of our code can be found at https://github.com/abaheti95/DC-NeuralConversation.

References in corpus (14)

• Sequence to Sequence Learning with Neural Networks
• How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
• Deep Reinforcement Learning for Dialogue Generation
• Chameleons in imagined conversations: A new approach to understanding coordination of linguistic style in dialogs
• Topic Aware Neural Response Generation
• A Simple, Fast Diverse Decoding Algorithm for Neural Generation
• Adversarial Learning for Neural Dialogue Generation
• Personalizing Dialogue Agents: I have a dog, do you have pets too?
• Mutual Information and Diverse Decoding Improve Neural Machine Translation
• Evaluating Prerequisite Qualities for Learning End-to-End Dialog Systems
• Learning Conversational Systems that Interleave Task and Non-Task Content
• Steering Output Style and Topic in Neural Response Generation
• Discourse-Aware Neural Rewards for Coherent Text Generation
• Polite Dialogue Generation Without Parallel Data

Cited by in corpus (5)

• End-to-End Trainable Non-Collaborative Dialog System
• Modeling Text-visual Mutual Dependency for Multi-modal Dialog Generation
• Non-Autoregressive Neural Dialogue Generation
• Large-scale Pretraining for Neural Machine Translation with Tens of Billions of Sentence Pairs
• Diversifying Topic-Coherent Response Generation for Natural Multi-turn Conversations