HSCJN: A Holistic Semantic Constraint Joint Network for Diverse Response Generation
This work addresses the challenge of generating varied and relevant responses in dialogue systems, representing an incremental improvement over existing Seq2Seq methods.
The paper tackles the problem of generating diverse and semantically consistent responses in dialogue systems by proposing HSCJN, a joint network that enhances global sentence information and penalizes low entropy output, resulting in improved performance over competitive methods on multiple dialogue corpora.
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.