activity
20202022
most citedRegularizing Dialogue Generation by Imitating Implicit Scenarios

4 citations · 9 across the 10 of their papers we have counts for

collaborators
Showing cs.CLShow all

10 papers · 1 filter

cs.CL2022

Towards Diverse, Relevant and Coherent Open-Domain Dialogue Generation via Hybrid Latent Variables

Bin Sun, Yitong Li, Fei Mi +3

Conditional variational models, using either continuous or discrete latent variables, are powerful for open-domain dialogue response generation. However, previous works show that c…

cs.CL20221 cited

Modeling Complex Dialogue Mappings via Sentence Semantic Segmentation Guided Conditional Variational Auto-Encoder

Bin Sun, Shaoxiong Feng, Yiwei Li +4

Complex dialogue mappings (CDM), including one-to-many and many-to-one mappings, tend to make dialogue models generate incoherent or dull responses, and modeling these mappings rem…

cs.CL20221 cited

Stop Filtering: Multi-View Attribute-Enhanced Dialogue Learning

Yiwei Li, Bin Sun, Shaoxiong Feng +1

There is a growing interest in improving the conversational ability of models by filtering the raw dialogue corpora. Previous filtering strategies usually rely on a scoring method…

cs.CL2022

Diversifying Neural Dialogue Generation via Negative Distillation

Yiwei Li, Shaoxiong Feng, Bin Sun +1

Generative dialogue models suffer badly from the generic response problem, limiting their applications to a few toy scenarios. Recently, an interesting approach, namely negative tr…

cs.CL20221 cited

Hierarchical Inductive Transfer for Continual Dialogue Learning

Shaoxiong Feng, Xuancheng Ren, Kan Li +1

Pre-trained models have achieved excellent performance on the dialogue task. However, for the continual increase of online chit-chat scenarios, directly fine-tuning these models fo…

cs.CL2021

Generating Relevant and Coherent Dialogue Responses using Self-separated Conditional Variational AutoEncoders

Bin Sun, Shaoxiong Feng, Yiwei Li +2

Conditional Variational AutoEncoder (CVAE) effectively increases the diversity and informativeness of responses in open-ended dialogue generation tasks through enriching the contex…