Yong Shan (单勇)

Master Candidate. NLP/ML
ICTNLP Group, Institute of Computing Technology, Chinese Academy of Sciences

Home

Publications

Internships

Awards

Social
Email
Scholar
GitHub

About Me

I am currently a second-year master student (Computer Science) at ICTNLP Group, Institute of Computing Technology, Chinese Academy of Sciences (ICT/CAS), under supervision of Prof. Yang Feng. Before studying in ICT/CAS, I obtained my bachelor’s degree (Electronic Engineering, National Innovative Education Key Class (2+2)) from Huazhong University of Science and Technology (HUST) in 2018.

My research interests include natural language processing and deep learning.

I'm looking for NLP jobs in industry.

Recent Publications

Yong Shan, Zekang Li, Jinchao Zhang, Fandong Meng, Yang Feng, Cheng Niu and Jie Zhou. A Contextual Hierarchical Attention Network with Adaptive Objective for Dialogue State Tracking. In Association for Computational Linguistics (ACL), 2020. (Long) [paper] [arxiv]

Recent studies in dialogue state tracking (DST) leverage historical information to determine states which are generally represented as slot-value pairs. However, most of them have limitations to efficiently exploit relevant context due to the lack of a powerful mechanism for modeling interactions between the slot and the dialogue history. Besides, existing methods usually ignore the slot imbalance problem and treat all slots indiscriminately, which limits the learning of hard slots and eventually hurts overall performance. In this paper, we propose to enhance the DST through employing a contextual hierarchical attention network to not only discern relevant information at both word level and turn level but also learn contextual representations. We further propose an adaptive objective to alleviate the slot imbalance problem by dynamically adjust weights of different slots during training. Experimental results show that our approach reaches 52.68% and 58.55% joint accuracy on MultiWOZ 2.0 and MultiWOZ 2.1 datasets respectively and achieves new state-of-the-art performance with considerable improvements (+1.24% and +5.98%).

Yong Shan, Yang Feng and Chenze Shao. Anonymous. In Empirical Methods in Natural Language Processing (EMNLP), 2020. (Under Review)

Yong Shan, Yang Feng, Jinchao Zhang, Fandong Meng and Wen Zhang. Improving Bidirectional Decoding with Dynamic Target Semantics for Neural Machine Translation. In CoRR. [arxiv]

Generally, Neural Machine Translation models generate target words in a left-to-right (L2R) manner and fail to exploit any future (right) semantics information, which usually produces an unbalanced translation. Recent works attempt to utilize the right-to-left (R2L) decoder in bidirectional decoding to alleviate this problem. In this paper, we propose a novel Dynamic Interaction Module (DIM) to dynamically exploit target semantics from R2L translation for enhancing the L2R translation quality. Different from other bidirectional decoding approaches, DIM firstly extracts helpful target information through addressing and reading operations, then updates target semantics for tracking the interactive history. Additionally, we further introduce an agreement regularization term into the training objective to narrow the gap between L2R and R2L translations. Experimental results on NIST Chinese-English and WMT'16 English-Romanian translation tasks show that our system achieves significant improvements over baseline systems, which also reaches comparable results compared to the state-of-the-art Transformer model with much fewer parameters of it.

Internships

Honors & Awards

Coming soon.