| Autor: |
Li, Xinzhe, Liu, Ming, Gao, Shang, Buntine, Wray |
| Rok vydání: |
2023 |
| Předmět: |
|
| Zdroj: |
IJCAI-2023 |
| Druh dokumentu: |
Working Paper |
| DOI: |
10.24963/ijcai.2023/749 |
| Popis: |
Adversarial robustness, domain generalization and dataset biases are three active lines of research contributing to out-of-distribution (OOD) evaluation on neural NLP models. However, a comprehensive, integrated discussion of the three research lines is still lacking in the literature. In this survey, we 1) compare the three lines of research under a unifying definition; 2) summarize the data-generating processes and evaluation protocols for each line of research; and 3) emphasize the challenges and opportunities for future work. |
| Databáze: |
arXiv |
| Externí odkaz: |
|
