Heming Xia
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Heming Xia has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Binghuai Lin
Tencent Cloud AI
1 shared publication - Peiyi Wang
School of Computer Science State Key Laboratory of Multimedia Information Processing Peking University
1 shared publication Tianyu Liu
Tencent Cloud AI
1 shared publication- Yunbo Cao
Tencent Cloud AI
1 shared publication Zhifang Sui
The MOE Key Laboratory of Computational Linguistics Peking University
1 shared publication
Latest Publications
- Open Access
Enhancing Continual Relation Extraction via Classifier Decomposition
Continual relation extraction (CRE) models aim at handling emerging new relations while avoiding catastrophically forgetting old ones in the streaming data. Though improvements have been shown by previous CRE studies, most of them only adopt a vanilla strategy when models first learn representations of new relations. In this work, we point out that there exist two typical biases after training of this vanilla strategy: classifier bias and representation bias, which causes the previous knowledge that the model learned to be shaded. To alleviate those biases, we propose a simple yet effective classifier decomposition framework that splits the last FFN layer into separated previous and current classifiers, so as to maintain previous knowledge and encourage the model to learn more robust representations at this training stage. Experimental results on two standard benchmarks show that our proposed framework consistently outperforms the state-of-the-art CRE models, which indicates that the importance of the first training stage to CRE models may be underestimated. Our code is available at https://github.com/hemingkx/CDec.
Open AccessEnhancing Continual Relation Extraction via Classifier Decomposition
Continual relation extraction (CRE) models aim at handling emerging new relations while avoiding catastrophically forgetting old ones in the streaming data. Though improvements have been shown by previous CRE studies, most of them only adopt a vanilla strategy when models first learn representations of new relations. In this work, we point out that there exist two typical biases after training of this vanilla strategy: classifier bias and representation bias, which causes the previous knowledge that the model learned to be shaded. To alleviate those biases, we propose a simple yet effective classifier decomposition framework that splits the last FFN layer into separated previous and current classifiers, so as to maintain previous knowledge and encourage the model to learn more robust representations at this training stage. Experimental results on two standard benchmarks show that our proposed framework consistently outperforms the state-of-the-art CRE models, which indicates that the importance of the first training stage to CRE models may be underestimated. Our code is available at https://github.com/hemingkx/CDec.