A Survey on Out-of-Distribution Evaluation of Neural NLP Models

Abstract

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. This survey will 1) compare the three lines of research under a unifying definition; 2) summarize their data-generating processes and evaluation protocols for each line of research; and 3) emphasize the challenges and opportunities for future work.

Cite

Text

Li et al. "A Survey on Out-of-Distribution Evaluation of Neural NLP Models." International Joint Conference on Artificial Intelligence, 2023. doi:10.24963/IJCAI.2023/749

Markdown

[Li et al. "A Survey on Out-of-Distribution Evaluation of Neural NLP Models." International Joint Conference on Artificial Intelligence, 2023.](https://mlanthology.org/ijcai/2023/li2023ijcai-survey/) doi:10.24963/IJCAI.2023/749

BibTeX

@inproceedings{li2023ijcai-survey,
  title     = {{A Survey on Out-of-Distribution Evaluation of Neural NLP Models}},
  author    = {Li, Xinzhe and Liu, Ming and Gao, Shang and Buntine, Wray L.},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2023},
  pages     = {6683-6691},
  doi       = {10.24963/IJCAI.2023/749},
  url       = {https://mlanthology.org/ijcai/2023/li2023ijcai-survey/}
}