Jiwei Li, Xiaoya Li, Yuxian Meng, Fei Wu, Shannon Ai, Tianwei Zhang, Jun Zhang, Chun Fan, ♣♠ Xiaofei
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Out-of-Distribution (OOD) detection is an important problem in natural language processing (NLP). In this work, we propose a simple yet effective framework kFolden, which mimics the behaviors of OOD detection during training without the use of any external data. For a task with k training labels, kFolden induces k sub-models, each of which is trained on a subset with k -1 categories with the left category masked unknown to the sub-model. Exposing an unknown label to the sub-model during training, the model is encouraged to learn to equally attribute the probability to the seen k -1 labels for the unknown label, enabling this framework to simultaneously resolve in-and out-distribution examples in a natural way via OOD simulations. Taking text classification as an archetype, we develop benchmarks for OOD detection using existing text classification datasets. By conducting comprehensive comparisons and analyses on the developed benchmarks, we demonstrate the superiority of kFolden against current methods in terms of improving OOD detection performances while maintaining improved in-domain classification accuracy. 1
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2108.12731")
get_code_for_paper("2108.12731")
have("2108.12731")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2108.12731.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2108.12731)
Connect an agent — have() is free.