Steering Output Style and Topic in Neural Response Generation

Abstract

We propose simple and flexible training and decoding methods for influencing output style and topic in neural encoder-decoder based language generation. This capability is desirable in a variety of applications, including conversational systems, where successful agents need to produce language in a specific style and generate responses steered by a human puppeteer or external knowledge. We decompose the neural generation process into empirically easier sub-problems: a faithfulness model and a decoding method based on selective-sampling. We also describe training and sampling algorithms that bias the generation process with a specific language style restriction, or a topic restriction. Human evaluation results show that our proposed methods are able to restrict style and topic without degrading output quality in conversational tasks.

arXiv commentEMNLP 2017 camera-ready version

References in corpus (9)

• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• A Neural Conversational Model
• How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
• Chameleons in imagined conversations: A new approach to understanding coordination of linguistic style in dialogs
• Topic Aware Neural Response Generation
• Incorporating Copying Mechanism in Sequence-to-Sequence Learning
• Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems
• Controlling Output Length in Neural Encoder-Decoders

Cited by in corpus (9)

• OpenViDial: A Large-Scale, Open-Domain Dialogue Dataset with Visual Contexts
• Conditional Text Generation for Harmonious Human-Machine Interaction
• Polite Dialogue Generation Without Parallel Data
• Better Conversations by Modeling,Filtering,and Optimizing for Coherence and Diversity
• Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints
• Why Do Neural Response Generation Models Prefer Universal Replies?
• Latent Topic Conversational Models
• Cue-word Driven Neural Response Generation with a Shrinking Vocabulary
• Predict and Use Latent Patterns for Short-Text Conversation