Predict and Use Latent Patterns for Short-Text Conversation
This work addresses the need for fine-grained control in neural conversation models, offering an incremental improvement over existing methods that use simpler latent words.
The paper tackled the problem of generating controlled and high-quality responses in short-text conversation by using detailed semantic forms like latent responses and part-of-speech sequences to guide generation, resulting in improved response diversity, fluency, and coherence.
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.