English

Focus-Constrained Attention Mechanism for CVAE-based Response Generation

Computation and Language 2020-09-28 v1

Abstract

To model diverse responses for a given post, one promising way is to introduce a latent variable into Seq2Seq models. The latent variable is supposed to capture the discourse-level information and encourage the informativeness of target responses. However, such discourse-level information is often too coarse for the decoder to be utilized. To tackle it, our idea is to transform the coarse-grained discourse-level information into fine-grained word-level information. Specifically, we firstly measure the semantic concentration of corresponding target response on the post words by introducing a fine-grained focus signal. Then, we propose a focus-constrained attention mechanism to take full advantage of focus in well aligning the input to the target response. The experimental results demonstrate that by exploiting the fine-grained signal, our model can generate more diverse and informative responses compared with several state-of-the-art models.

Keywords

Cite

@article{arxiv.2009.12102,
  title  = {Focus-Constrained Attention Mechanism for CVAE-based Response Generation},
  author = {Zhi Cui and Yanran Li and Jiayi Zhang and Jianwei Cui and Chen Wei and Bin Wang},
  journal= {arXiv preprint arXiv:2009.12102},
  year   = {2020}
}

Comments

To appear in findings of EMNLP 2020

R2 v1 2026-06-23T18:47:21.809Z