most citedMulti-Object Tracking with Multiple Cues and Switcher-Aware Classification

90 citations · 116 across the 5 of their papers we have counts for

collaborators

5 papers

cs.CL20196 cited

Neural Response Generation with Meta-Words

Can Xu, Wei Wu, Chongyang Tao +3

We present open domain response generation with meta-words. A meta-word is a structured record that describes various attributes of a response, and thus allows us to explicitly mod…

cs.CL20197 cited

Learning a Matching Model with Co-teaching for Multi-turn Response Selection in Retrieval-based Dialogue Systems

Jiazhan Feng, Chongyang Tao, Wei Wu +3

We study learning of a matching model for response selection in retrieval-based dialogue systems. The problem is equally important with designing the architecture of a model, but i…

cs.CL20195 cited

A Document-grounded Matching Network for Response Selection in Retrieval-based Chatbots

Xueliang Zhao, Chongyang Tao, Wei Wu +3

We present a document-grounded matching network (DGMN) for response selection that can power a knowledge-aware retrieval-based chatbot system. The challenges of building such a mod…

cs.CV201990 cited

Multi-Object Tracking with Multiple Cues and Switcher-Aware Classification

Weitao Feng, Zhihao Hu, Wei Wu +2

In this paper, we propose a unified Multi-Object Tracking (MOT) framework learning to make full use of long term and short term cues for handling complex cases in MOT scenes. Besid…

cs.CL20168 cited

Detecting Context Dependent Messages in a Conversational Environment

Chaozhuo Li, Yu Wu, Wei Wu +3

While automatic response generation for building chatbot systems has drawn a lot of attention recently, there is limited understanding on when we need to consider the linguistic co…