Jian Yang

Jian Yang

Auto-generated profile, based on publicly available information

Jian Yang

Beihang University, Beijing, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
1 January 2025
Verified
Conference Paper
Open access
PDF file
QPQiyao Peng
Qiyao Peng
HLHongtao Liu
Hongtao Liu
HHHua Huang
Hua Huang
JYJian Yang
Jian Yang
QYQing Yang
Qing Yang
MSMinglai Shao
Minglai Shao
Qiyao Peng, Hongtao Liu, Hua Huang, Jian Yang, Qing Yang, Minglai Shao. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.

2 January 2026
Verified
Book Chapter
Closed access
PDF file
BWBing Wang
Bing Wang
XLXinnian Liang
Xinnian Liang
JYJian Yang
Jian Yang
HHHui Huang
Hui Huang
ZWZhenhe Wu
Zhenhe Wu
ZLZhoujun Li
Zhoujun Li

10 November 2022 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
JYJian Yang
Jian Yang
YYYuwei Yin
Yuwei Yin
LYLiqun Yang
Liqun Yang
SMShuming Ma
Shuming Ma
HHHaoyang Huang
Haoyang Huang
ZLZhoujun Li
Zhoujun Li
Transformer structure, stacked by a sequence of encoder and decoder network layers, achieves significant development in neural machine translation. However, vanilla Transformer mainly exploits the top-layer representation, assuming the lower layers provide trivial or redundant information and thus ignoring the bottom-layer feature that is potentially valuable. In this work, we propose the G roup- Trans former model ( GTrans ) that flexibly divides multi-layer representations of both encoder and decoder into different groups and then fuses these group features to generate target words. To corroborate the effectiveness of the proposed method, extensive experiments and analytic experiments are conducted on three bilingual translation benchmarks and three multilingual translation tasks, including the IWLST-14, IWLST-17, LDC, WMT-14, WMT-21 and OPUS-100 benchmark. Experimental and analytical results demonstrate that our model outperforms its Transformer counterparts by a consistent gain. Furthermore, it can be successfully scaled up to 60 encoder layers and 36 decoder layers.

30 January 2023 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
JBJiaqi Bai
Jiaqi Bai
ZYZe Yang
Ze Yang
JYJian Yang
Jian Yang
HGHugo Guo
Hugo Guo
ZLZhoujun Li
Zhoujun Li
Knowledge-grounded conversation has led to great progress in producing informative dialog responses by leveraging external knowledge. This work focuses on two affiliated knowledge grounded conversation tasks: Knowledge Selection and Response Generation . Previous work followed the paradigm of selecting the most optimal knowledge piece to guide the conversation towards generating the proper response. However, some knowledge pieces, which are not recognized as optimal, may still benefit response generation. How to effectively leverage these relevant knowledge pieces for response generation still remain a tricky issue. To address this problem, we propose KIN ET , a Knowledge Incorporation Network, which deals with the problem by boosting both the knowledge selection and the response generation. The proposed model contains a negative enhanced knowledge approximator which improves knowledge selection by enhancing the dense representation of knowledge pieces, and a curriculum knowledge sampler which improves generated responses by incorporating more relevant knowledge pieces in an easy-to-hard manner. We conduct the experiment on two datasets of knowledge-grounded conversations, the results show that the proposed model significantly outperforms state-of-the-art methods in terms of both automatic and human evaluations.

14 April 2023
Verified
Book Chapter
Closed access
PDF file
HGHugo Guo
Hugo Guo
YGYuhui Guo
Yuhui Guo
JYJian Yang
Jian Yang
JLJiaheng Liu
Jiaheng Liu
ZLZhoujun Li
Zhoujun Li
BZBo Zhang
Bo Zhang

21 October 2023
Verified
Conference Paper
Open access
JBJiaqi Bai
Jiaqi Bai
HGHugo Guo
Hugo Guo
JLJiaheng Liu
Jiaheng Liu
JYJian Yang
Jian Yang
XLXinnian Liang
Xinnian Liang
ZLZhoujun Li
Zhoujun Li
Retrieval-enhanced text generation has shown remarkable progress on knowledge-intensive language tasks, such as open-domain question answering and knowledge-enhanced dialogue generation, by leveraging passages retrieved from a large passage corpus for delivering a proper answer given the input query. However, the retrieved passages are not ideal for guiding answer generation because of the discrepancy between retrieval and generation, i.e., the candidate passages are all treated equally during the retrieval procedure without considering their potential to generate a proper answer. This discrepancy makes a passage retriever deliver a sub-optimal collection of candidate passages to generate the answer. In this paper, we propose the GeneRative Knowledge Improved Passage Ranking (GripRank) approach, addressing the above challenge by distilling knowledge from a generative passage estimator (GPE) to a passage ranker, where the GPE is a generative language model used to measure how likely the candidate passages can generate the proper answer. We realize the distillation procedure by teaching the passage ranker learning to rank the passages ordered by the GPE. Furthermore, we improve the distillation quality by devising a curriculum knowledge distillation mechanism, which allows the knowledge provided by the GPE can be progressively distilled to the ranker through an easy-to-hard curriculum, enabling the passage ranker to correctly recognize the provenance of the answer from many plausible candidates. We conduct extensive experiments on four datasets across three knowledge-intensive language tasks. Experimental results show advantages over the state-of-the-art methods for both passage ranking and answer generation on the KILT benchmark.