Run Lin

Run Lin

Auto-generated profile, based on publicly available information

Run Lin

University of Electronic Science and Technology of China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
24 March 2024 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
DLDa Luo
Da Luo
YGYanglei Gan
Yanglei Gan
RHRui Hou
Rui Hou
RLRun Lin
Run Lin
QLQiao Liu
Qiao Liu
WGWannian Gao
Wannian Gao
Few-shot Relation Extraction (FSRE) aims to extract relational facts from a sparse set of labeled corpora. Recent studies have shown promising results in FSRE by employing Pre-trained Language Models (PLMs) within the framework of supervised contrastive learning, which considers both instances and label facts. However, how to effectively harness massive instance-label pairs to encompass the learned representation with semantic richness in this learning paradigm is not fully explored. To address this gap, we introduce a novel synergistic anchored contrastive pre-training framework. This framework is motivated by the insight that the diverse viewpoints conveyed through instance-label pairs capture incomplete yet complementary intrinsic textual semantics. Specifically, our framework involves a symmetrical contrastive objective that encompasses both sentence-anchored and label-anchored contrastive losses. By combining these two losses, the model establishes a robust and uniform representation space. This space effectively captures the reciprocal alignment of feature distributions among instances and relational facts, simultaneously enhancing the maximization of mutual information across diverse perspectives within the same relation. Experimental results demonstrate that our framework achieves significant performance enhancements compared to baseline models in downstream FSRE tasks. Furthermore, our approach exhibits superior adaptability to handle the challenges of domain shift and zero-shot relation extraction. Our code is available online at https://github.com/AONE-NLP/FSRE-SaCon.

24 July 2024 in Expert Systems with Applications
Verified
Journal Article
Closed access
KAKhwaja Mutahir Ahmad
Khwaja Mutahir Ahmad
QLQiao Liu
Qiao Liu
AKAbdullah Aman Khan
Abdullah Aman Khan
YGYanglei Gan
Yanglei Gan
RLRun Lin
Run Lin

1 January 2024
Verified
Conference Paper
Open access
PDF file
YCYuxiang Cai
Yuxiang Cai
QLQiao Liu
Qiao Liu
YGYanglei Gan
Yanglei Gan
CLChanglin Li
Changlin Li
XLXueyi Liu
Xueyi Liu
JJJiayeYang JiayeYang
JiayeYang JiayeYang
Yuxiang Cai, Qiao Liu, Yanglei Gan, Changlin Li, Xueyi Liu, Run Lin, Da Luo, JiayeYang JiayeYang. Findings of the Association for Computational Linguistics ACL 2024. 2024.

28 December 2024 in Expert Systems with Applications
Verified
Journal Article
Closed access
RLRun Lin
Run Lin
YGYanglei Gan
Yanglei Gan
TLTian Lan
Tian Lan
XLXueyi Liu
Xueyi Liu
YCYuxiang Cai
Yuxiang Cai
QLQiao Liu
Qiao Liu

20 February 2026 in Knowledge-Based Systems
Verified
Journal Article
Closed access
PHPeng He
Peng He
YGYanglei Gan
Yanglei Gan
YLYuxiang Liu
Yuxiang Liu
RLRun Lin
Run Lin
GZGuanyu Zhou
Guanyu Zhou
QLQiao Liu
Qiao Liu

17 November 2025 in Neural Networks
Verified
Journal Article
Closed access
YGYanglei Gan
Yanglei Gan
YLYao Liu
Yao Liu
YCYuxiang Cai
Yuxiang Cai
RLRun Lin
Run Lin
SYSong Yang
Song Yang
XSXiaojun Shi
Xiaojun Shi