HSCJN: A Holistic Semantic Constraint Joint Network for Diverse Response Generation

TL;DR

This paper introduces HSCJN, a novel neural network that enhances response diversity and semantic consistency in dialogue generation by incorporating holistic semantic constraints and entropy regularization.

Contribution

The paper proposes a generic, diversity-promoting joint network that improves semantic relevance and diversity in Seq2Seq dialogue models, applicable to various architectures.

Findings

Improves response diversity in dialogue generation.

Enhances semantic consistency of generated responses.

Outperforms existing methods on multiple dialogue datasets.

Abstract

The sequence-to-sequence (Seq2Seq) model generates target words iteratively given the previously observed words during decoding process, which results in the loss of the holistic semantics in the target response and the complete semantic relationship between responses and dialogue histories. In this paper, we propose a generic diversity-promoting joint network, called Holistic Semantic Constraint Joint Network (HSCJN), enhancing the global sentence information, and then regularizing the objective function with penalizing the low entropy output. Our network introduces more target information to improve diversity, and captures direct semantic information to better constrain the relevance simultaneously. Moreover, the proposed method can be easily applied to any Seq2Seq structure. Extensive experiments on several dialogue corpuses show that our method effectively improves both semantic consistency and diversity of generated responses, and achieves better performance than other competitive methods.