Focus-Constrained Attention Mechanism for CVAE-based Response Generation

by   Zhi Cui, et al.

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.


page 1

page 2

page 3

page 4


Predict and Use Latent Patterns for Short-Text Conversation

Many neural network models nowadays have achieved promising performances...

Fine-Grained Attention Mechanism for Neural Machine Translation

Neural machine translation (NMT) has been a new paradigm in machine tran...

Generating Multiple Diverse Responses with Multi-Mapping and Posterior Mapping Selection

In human conversation an input post is open to multiple potential respon...

Enhancing Dialogue Generation via Multi-Level Contrastive Learning

Most of the existing works for dialogue generation are data-driven model...

Leveraging Multi-grained Sentiment Lexicon Information for Neural Sequence Models

Neural sequence models have achieved great success in sentence-level sen...

CASE: Aligning Coarse-to-Fine Cognition and Affection for Empathetic Response Generation

Empathy is a trait that naturally manifests in human conversation. Theor...

PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning

To build a high-quality open-domain chatbot, we introduce the effective ...