Lei Shen

Lei Shen

Auto-generated profile, based on publicly available information

Lei Shen

JD AI Research, Beijing, China

Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2020
Verified
Conference Paper
Open access
PDF file
LSLei Shen
Lei Shen
YFYang Feng
Yang Feng
Lei Shen, Yang Feng. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2020.

1 May 2010 in Science China Technological Sciences
Verified
Journal Article
Closed access
PDF file
ZCZhuo Chen
Zhuo Chen
LSLei Shen
Lei Shen
YZYanQing Zhao
YanQing Zhao
CYChongjun Yang
Chongjun Yang

1 January 2018
Verified
Conference Paper
Open access
WZWen Zhang
Wen Zhang
LHLiang Huang
Liang Huang
YFYang Feng
Yang Feng
LSLei Shen
Lei Shen
QLQun Liu
Qun Liu

1 January 2019
Verified
Conference Paper
Open access
LSLei Shen
Lei Shen
YFYang Feng
Yang Feng
HZHaolan Zhan
Haolan Zhan

6 June 2021
Verified
Conference Paper
Open access
LSLei Shen
Lei Shen
HZHaolan Zhan
Haolan Zhan
XSXin Shen
Xin Shen
FYFeng Yang
Feng Yang
Open-domain multi-turn conversations mainly have three features, which are hierarchical semantic structure, redundant information, and long-term dependency. Grounded on these, selecting relevant context becomes a challenge step for multiturn dialogue generation. However, existing methods cannot differentiate both useful words and utterances in long distances from a response. Besides, previous work just performs context selection based on a state in the decoder, which lacks a global guidance and could lead some focuses on irrelevant or unnecessary information. In this paper, we propose a novel model with hierarchical self-attention mechanism and distant supervision to not only detect relevant words and utterances in short and long distances, but also discern related information globally when decoding. Experimental results on two public datasets of both automatic and human evaluations show that our model significantly outperforms other baselines in terms of fluency, coherence, and informativeness.

1 July 2020
Verified
Conference Paper
Open access
LSLei Shen
Lei Shen
XGXiaoyu Guo
Xiaoyu Guo
MCMeng Chen
Meng Chen
Chinese poetry is an important part of worldwide culture, and classical and modern sub-branches are quite different. The former is a unique genre and has strict constraints, while the latter is very flexible in length, optional to have rhymes, and similar to modern poetry in other languages. Thus, it requires more to control the coherence and improve the novelty. In this paper, we propose a generate-retrieve-then-refine paradigm to jointly improve the coherence and novelty. In the first stage, a draft is generated given keywords (i.e., topics) only. The second stage produces a "refining vector" from retrieval lines. At last, we take into consideration both the draft and the "refining vector" to generate a new poem. The draft provides future sentence-level information for a line to be generated. Meanwhile, the "refining vector" points out the direction of refinement based on impressive words detection mechanism which can learn good patterns from references and then create new ones via insertion operation. Experimental results on a collected large-scale modern Chinese poetry dataset show that our proposed approach can not only generate more coherent poems, but also improve the diversity and novelty.