On Robustness and Bias Analysis of BERT-based Relation Extraction

September 14, 2020 ยท Declared Dead ยท ๐Ÿ› China Conference on Knowledge Graph and Semantic Computing

๐Ÿ’€ CAUSE OF DEATH: 404 Not Found
Code link is broken/dead
Authors Luoqiu Li, Xiang Chen, Hongbin Ye, Zhen Bi, Shumin Deng, Ningyu Zhang, Huajun Chen arXiv ID 2009.06206 Category cs.CL: Computation & Language Cross-listed cs.AI, cs.DB, cs.IR, cs.LG Citations 20 Venue China Conference on Knowledge Graph and Semantic Computing Repository https://github.com/zjunlp/DiagnoseRE} Last Checked 2 months ago
Abstract
Fine-tuning pre-trained models have achieved impressive performance on standard natural language processing benchmarks. However, the resultant model generalizability remains poorly understood. We do not know, for example, how excellent performance can lead to the perfection of generalization models. In this study, we analyze a fine-tuned BERT model from different perspectives using relation extraction. We also characterize the differences in generalization techniques according to our proposed improvements. From empirical experimentation, we find that BERT suffers a bottleneck in terms of robustness by way of randomizations, adversarial and counterfactual tests, and biases (i.e., selection and semantic). These findings highlight opportunities for future improvements. Our open-sourced testbed DiagnoseRE is available in \url{https://github.com/zjunlp/DiagnoseRE}.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Computation & Language

๐ŸŒ… ๐ŸŒ… Old Age

Attention Is All You Need

Ashish Vaswani, Noam Shazeer, ... (+6 more)

cs.CL ๐Ÿ› NeurIPS ๐Ÿ“š 166.0K cites 8 years ago

Died the same way โ€” ๐Ÿ’€ 404 Not Found