Types of Out-of-Distribution Texts and How to Detect Them
arXiv:2109.06827
Abstract
Despite agreement on the importance of detecting out-of-distribution (OOD) examples, there is little consensus on the formal definition of OOD examples and how to best detect them. We categorize these examples by whether they exhibit a background shift or a semantic shift, and find that the two major approaches to OOD detection, model calibration and density estimation (language modeling for text), have distinct behavior on these types of OOD data. Across 14 pairs of in-distribution and OOD English natural language understanding datasets, we find that density estimation methods consistently beat calibration methods in background shift settings, while performing worse in semantic shift settings. In addition, we find that both methods generally fail to detect examples from challenge data, highlighting a weak spot for current methods. Since no single method works well across all settings, our results call for an explicit definition of OOD examples when evaluating different detection methods.
arXiv commentEMNLP 2021
References in corpus (9)
- A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
- Frustratingly Easy Domain Adaptation
- WILDS: A Benchmark of in-the-Wild Distribution Shifts
- A Survey of Domain Adaptation for Neural Machine Translation
- Scaling Out-of-Distribution Detection for Real-World Settings
- Contrastive Out-of-Distribution Detection for Pretrained Transformers
- Hybrid Models with Deep and Invertible Features
- Misinformation Has High Perplexity
- Hybrid Discriminative-Generative Training via Contrastive Learning