Preserving Knowledge Invariance: Rethinking Robustness Evaluation of Open Information Extraction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929699207249920 |
|---|---|
| author | Qi, Ji Zhang, Chuchun Wang, Xiaozhi Zeng, Kaisheng Yu, Jifan Liu, Jinxin Sun, Jiuding Chen, Yuxiang Hou, Lei Li, Juanzi Xu, Bin |
| author_facet | Qi, Ji Zhang, Chuchun Wang, Xiaozhi Zeng, Kaisheng Yu, Jifan Liu, Jinxin Sun, Jiuding Chen, Yuxiang Hou, Lei Li, Juanzi Xu, Bin |
| contents | The robustness to distribution changes ensures that NLP models can be successfully applied in the realistic world, especially for information extraction tasks. However, most prior evaluation benchmarks have been devoted to validating pairwise matching correctness, ignoring the crucial measurement of robustness. In this paper, we present the first benchmark that simulates the evaluation of open information extraction models in the real world, where the syntactic and expressive distributions under the same knowledge meaning may drift variously. We design and annotate a large-scale testbed in which each example is a knowledge-invariant clique that consists of sentences with structured knowledge of the same meaning but with different syntactic and expressive forms. By further elaborating the robustness metric, a model is judged to be robust if its performance is consistently accurate on the overall cliques. We perform experiments on typical models published in the last decade as well as a popular large language model, the results show that the existing successful models exhibit a frustrating degradation, with a maximum drop of 23.43 F1 score. Our resources and code are available at https://github.com/qijimrc/ROBUST. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_13981 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Preserving Knowledge Invariance: Rethinking Robustness Evaluation of Open Information Extraction Qi, Ji Zhang, Chuchun Wang, Xiaozhi Zeng, Kaisheng Yu, Jifan Liu, Jinxin Sun, Jiuding Chen, Yuxiang Hou, Lei Li, Juanzi Xu, Bin Computation and Language Artificial Intelligence The robustness to distribution changes ensures that NLP models can be successfully applied in the realistic world, especially for information extraction tasks. However, most prior evaluation benchmarks have been devoted to validating pairwise matching correctness, ignoring the crucial measurement of robustness. In this paper, we present the first benchmark that simulates the evaluation of open information extraction models in the real world, where the syntactic and expressive distributions under the same knowledge meaning may drift variously. We design and annotate a large-scale testbed in which each example is a knowledge-invariant clique that consists of sentences with structured knowledge of the same meaning but with different syntactic and expressive forms. By further elaborating the robustness metric, a model is judged to be robust if its performance is consistently accurate on the overall cliques. We perform experiments on typical models published in the last decade as well as a popular large language model, the results show that the existing successful models exhibit a frustrating degradation, with a maximum drop of 23.43 F1 score. Our resources and code are available at https://github.com/qijimrc/ROBUST. |
| title | Preserving Knowledge Invariance: Rethinking Robustness Evaluation of Open Information Extraction |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2305.13981 |