Improving Open-Domain Dialogue Systems via Multi-Turn Incomplete Utterance Restoration

no code implementations • IJCNLP 2019 • Zhufeng Pan, Kun Bai, Yan Wang, Lianqiang Zhou, Xiaojiang Liu

To facilitate the study of incomplete utterance restoration for open-domain dialogue systems, a large-scale multi-turn dataset Restoration-200K is collected and manually labeled with the explicit relation between an utterance and its context.

Hallucinating Optical Flow Features for Video Classification

1 code implementation • 28 May 2019 • Yongyi Tang, Lin Ma, Lianqiang Zhou

However, extracting motion information, specifically in the form of optical flow features, is extremely computationally expensive, especially for large-scale video classification.

Classification General Classification +3

Context-Sensitive Generation of Open-Domain Conversational Responses

no code implementations • COLING 2018 • Wei-Nan Zhang, Yiming Cui, Yifa Wang, Qingfu Zhu, Lingzhi Li, Lianqiang Zhou, Ting Liu

Despite the success of existing works on single-turn conversation generation, taking the coherence in consideration, human conversing is actually a context-sensitive process.

Information Retrieval Machine Translation

Learning to Start for Sequence to Sequence Architecture

no code implementations • 19 Aug 2016 • Qingfu Zhu, Wei-Nan Zhang, Lianqiang Zhou, Ting Liu

An obvious drawback of these work is that there is not a learnable relationship between words and the start symbol.

Machine Translation Response Generation +3