Modeling Complex Dialogue Mappings via Sentence Semantic Segmentation Guided Conditional Variational Auto-Encoder

TL;DR

This paper introduces SegCVAE, a novel model that effectively captures complex dialogue mappings by leveraging sentence semantic segmentation, leading to improved dialogue generation quality and state-of-the-art results.

Contribution

SegCVAE is the first model to explicitly utilize semantic segmentation to model complex dialogue mappings, enhancing understanding and diversity in responses.

Findings

Achieves state-of-the-art performance on dialogue generation tasks.

Improves response coherence and diversity through semantic-guided latent variables.

Outperforms existing methods in automatic and human evaluations.

Abstract

Complex dialogue mappings (CDM), including one-to-many and many-to-one mappings, tend to make dialogue models generate incoherent or dull responses, and modeling these mappings remains a huge challenge for neural dialogue systems. To alleviate these problems, methods like introducing external information, reconstructing the optimization function, and manipulating data samples are proposed, while they primarily focus on avoiding training with CDM, inevitably weakening the model's ability of understanding CDM in human conversations and limiting further improvements in model performance. This paper proposes a Sentence Semantic \textbf{Seg}mentation guided \textbf{C}onditional \textbf{V}ariational \textbf{A}uto-\textbf{E}ncoder (SegCVAE) method which can model and take advantages of the CDM data. Specifically, to tackle the incoherent problem caused by one-to-many, SegCVAE uses response-related prominent semantics to constrained the latent variable. To mitigate the non-diverse problem brought by many-to-one, SegCVAE segments multiple prominent semantics to enrich the latent variables. Three novel components, Internal Separation, External Guidance, and Semantic Norms, are proposed to achieve SegCVAE. On dialogue generation tasks, both the automatic and human evaluation results show that SegCVAE achieves new state-of-the-art performance.