Beijing Institute of Technology
Author pages are created from data sourced from our academic publisher partnerships and public sources.
Share This Author
Posterior-GAN: Towards Informative and Coherent Response Generation with Posterior Generative Adversarial Network
A novel encoder-decoder based generative adversarial learning framework, Posterior Generative Adversarial Network (Posterior-GAN), which consists of a forward and a backward generative discriminator to cooperatively encourage the generated response to be informative and coherent by two complementary assessment perspectives is proposed.
Generating Relevant and Coherent Dialogue Responses using Self-separated Conditional Variational AutoEncoders
Self-separated Conditional Variational AutoEncoder (abbreviated as SepaCVAE) is proposed that introduces group information to regularize the latent variables, which enhances CVAE by improving the responses’ relevance and coherence while maintaining their diversity and informativeness.
Regularizing Dialogue Generation by Imitating Implicit Scenarios
- Shaoxiong Feng, Xuancheng Ren, Hongshen Chen, Bin Sun, K. Li, Xu Sun
- Computer ScienceEMNLP
- 5 October 2020
This work proposes to improve generative dialogue systems from the scenario perspective, where both dialogue history and future conversation are taken into account to implicitly reconstruct the scenario knowledge.
Multi-View Feature Representation for Dialogue Generation with Bidirectional Distillation
A novel training framework that extends the unidirectionaldistillation to the bidirectional distillation that encourages the student and its student peers to co-evolve by exchanging complementary knowledge with each other and improves the model generalization without sacrificing training efficiency.
Collaborative Group Learning
- Shaoxiong Feng, Hongshen Chen, Xuancheng Ren, Zhuoye Ding, K. Li, Xu Sun
- Computer Science, MathematicsAAAI
- 16 September 2020
Empirical evaluations indicate that the proposed Collaborative Group Learning method significantly outperforms various state-of-the-art collaborative approaches whilst enhancing computational efficiency.
Continue or SHIFT: Learning Conversational Patterns for Dialogue Generation
In dialogues, it is often the case that the response could be either relevant or irrelevant to the given conversation context, depending on the speaker’s intention of either topic continuity or topic…
THINK: A Novel Conversation Model for Generating Grammatically Correct and Coherent Responses
This work proposed a conversation model named “THINK” (Teamwork generation Hover around Impressive Noticeable Keywords) to make the decoder more complicated and avoid generating duplicated and selfcontradicting responses.