Junzhe Chen

Junzhe Chen

Auto-generated profile, based on publicly available information

Junzhe Chen

Tsinghua University, Beijing, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
18 July 2023
Verified
Conference Paper
Open access
XHXuming Hu
Xuming Hu
ZGZhijiang Guo
Zhijiang Guo
JCJunzhe Chen
Junzhe Chen
LWLijie Wen
Lijie Wen
PYPhilip S. Yu
Philip S. Yu

26 October 2023
Verified
Conference Paper
Open access
XHXuming Hu
Xuming Hu
JCJunzhe Chen
Junzhe Chen
ALAiwei Liu
Aiwei Liu
SMShiao Meng
Shiao Meng
LWLijie Wen
Lijie Wen
PYPhilip S. Yu
Philip S. Yu
How can we better extract entities and relations from text? Using multimodal extraction with images and text obtains more signals for entities and relations, and aligns them through graphs or hierarchical fusion, aiding in extraction. Despite attempts at various fusions, previous works have overlooked many unlabeled image-caption pairs, such as NewsCLIPing. This paper proposes innovative pre-training objectives for entity-object and relation-image alignment, extracting objects from images and aligning them with entity and relation prompts for soft pseudo-labels. These labels are used as self-supervised signals for pre-training, enhancing the ability to extract entities and relations. Experiments on three datasets show an average 3.41% F1 improvement over prior SOTA. Additionally, our method is orthogonal to previous multimodal fusions, and using it on prior SOTA fusions further improves 5.47% F1.

18 July 2023
Verified
Conference Paper
Open access
XHXuming Hu
Xuming Hu
JCJunzhe Chen
Junzhe Chen
SMShiao Meng
Shiao Meng
LWLijie Wen
Lijie Wen
PYPhilip S. Yu
Philip S. Yu
Low-resource relation extraction (LRE) aims to extract potential relations from limited labeled corpus to handle the problem of scarcity of human annotations. Previous works mainly consist of two categories of methods: (1) Self-training methods, which improve themselves through the models' predictions, thus suffering from confirmation bias when the predictions are wrong. (2) Self-ensembling methods, which learn task-agnostic representations, therefore, generally do not work well for specific tasks. In our work, we propose a novel LRE architecture named SelfLRE, which leverages two complementary modules, one module uses self-training to obtain pseudo-labels for unlabeled data, and the other module uses self-ensembling learning to obtain the task-agnostic representations, and leverages the existing pseudo-labels to refine the better task-specific representations on unlabeled data. The two models are jointly trained through multi-task learning to iteratively improve the effect of LRE task. Experiments on three public datasets show that SelfLRE achieves 1.81% performance gain over the SOTA baseline. Source code is available at: https://github.com/THU-BPM/SelfLRE.