Predict and Use Latent Patterns for Short-Text Conversation

Abstract

Many neural network models nowadays have achieved promising performances in Chit-chat settings. The majority of them rely on an encoder for understanding the post and a decoder for generating the response. Without given assigned semantics, the models lack the fine-grained control over responses as the semantic mapping between posts and responses is hidden on the fly within the end-to-end manners. Some previous works utilize sampled latent words as a controllable semantic form to drive the generated response around the work, but few works attempt to use more complex semantic patterns to guide the generation. In this paper, we propose to use more detailed semantic forms, including latent responses and part-of-speech sequences sampled from the corresponding distributions, as the controllable semantics to guide the generation. Our results show that the richer semantics are not only able to provide informative and diverse responses, but also increase the overall performance of response quality, including fluency and coherence.

References in corpus (13)

• A Neural Conversational Model
• Sequence Level Training with Recurrent Neural Networks
• Deep Reinforcement Learning for Dialogue Generation
• A Simple, Fast Diverse Decoding Algorithm for Neural Generation
• Adversarial Learning for Neural Dialogue Generation
• An Information Retrieval Approach to Short Text Conversation
• A Retrieve-and-Edit Framework for Predicting Structured Outputs
• Two are Better than One: An Ensemble of Retrieval- and Generation-Based Dialog Systems
• A Neural Network Approach to Context-Sensitive Generation of Conversational Responses
• Retrieve and Refine: Improved Sequence Generation Models For Dialogue
• Steering Output Style and Topic in Neural Response Generation
• Fine-Grained Sentence Functions for Short-Text Conversation
• A Discrete CVAE for Response Generation on Short-Text Conversation