Jijie Li

Jijie Li

Auto-generated profile, based on publicly available information

Jijie Li

State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications

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 2022
Verified
Conference Paper
Open access
PDF file
JGJinyu Guo
Jinyu Guo
KSKai Shuang
Kai Shuang
JLJijie Li
Jijie Li
ZWZihan Wang
Zihan Wang
YLYixuan Liu
Yixuan Liu
Jinyu Guo, Kai Shuang, Jijie Li, Zihan Wang, Yixuan Liu. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2022.

1 January 2021
Verified
Conference Paper
Open access
PDF file
JGJinyu Guo
Jinyu Guo
KSKai Shuang
Kai Shuang
JLJijie Li
Jijie Li
ZWZihan Wang
Zihan Wang
Jinyu Guo, Kai Shuang, Jijie Li, Zihan Wang. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

24 April 2023 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
JLJijie Li
Jijie Li
KSKai Shuang
Kai Shuang
JGJinyu Guo
Jinyu Guo
ZSZengyi Shi
Zengyi Shi
HWHongman Wang
Hongman Wang
Relation Classification (RC) is a basic and essential task of Natural Language Processing. Existing RC methods can be classified into two categories: sequence-based methods and dependency-based methods. Sequence-based methods identify the target relation based on the overall semantics of the whole sentence, which will inevitably introduce noisy features. Dependency-based methods extract indicative word-level features from the Shortest Dependency Path (SDP) between given entities and attempt to establish a statistical association between the words and the target relations. This pattern relatively eliminates the influence of noisy features and achieves a robust performance on long sentences. Nevertheless, we observe that majority of relation classification processes involve complex semantic reasoning which is hard to be achieved based on the word-level statistical association. To solve this problem, we categorize all relations into atomic relations and composed-relations. The atomic relations are the basic relations that can be identified based on the word-level features, while the composed-relation requires to be deducted from multiple atomic relations. Correspondingly, we propose the At omic Relation E ncoding and R easoning M odel (ATERM). In the atomic relation encoding stage, ATERM groups the word-level features and encodes multiple atomic relations in parallel. In the atomic relation reasoning stage, ATERM establishes the atomic relation chain where relation-level features are extracted to identify composed-relations. Experiments show that our method achieves state-of-the-art results on the three most popular relation classification datasets – TACRED, TACRED-Revisit, and SemEval 2010 task 8 with significant improvements.