C
Cheng Niu
Researcher at Tencent
Publications - 18
Citations - 448
Cheng Niu is an academic researcher from Tencent. The author has contributed to research in topics: Context (language use) & Transformer (machine learning model). The author has an hindex of 8, co-authored 18 publications receiving 284 citations.
Papers
More filters
Proceedings ArticleDOI
Improving Multi-turn Dialogue Modelling with Utterance ReWriter
TL;DR: The authors proposed rewriting human utterance as a pre-process to help multi-turn dialgoue modeling. But the task of utterance rewriting was not addressed in this paper.
Posted Content
Incremental Transformer with Deliberation Decoder for Document Grounded Conversations
TL;DR: This article proposed an incremental transformer-based approach to encode multi-turn utterances along with knowledge in related documents, and designed a two-pass decoder to improve context coherence and knowledge correctness.
Proceedings ArticleDOI
Incremental Transformer with Deliberation Decoder for Document Grounded Conversations.
TL;DR: This paper designs an Incremental Transformer to encode multi-turn utterances along with knowledge in related documents and designs a two-pass decoder (Deliberation Decoder) to improve context coherence and knowledge correctness.
Proceedings ArticleDOI
Neural Data-to-Text Generation via Jointly Learning the Segmentation and Correspondence
TL;DR: This work proposes to explicitly segment target text into fragment units and align them with their data correspondences to maintain the same expressive power as neural attention models, while being able to generate fully interpretable outputs with several times less computational cost.
Proceedings ArticleDOI
A Contextual Hierarchical Attention Network with Adaptive Objective for Dialogue State Tracking
TL;DR: This article proposed a contextual hierarchical attention network to not only discern relevant information at both word level and turn level, but also learn contextual representations to alleviate the slot imbalance problem by dynamically adjust weights of different slots during training.