Semantic Role Labeling Guided Out-of-distribution Detection
This addresses the challenge of identifying domain-shifted instances in NLP applications, which is crucial for real-world deployment, but it appears incremental as it builds on existing OOD detection methods.
The paper tackles the problem of detecting out-of-distribution instances in natural language processing by proposing SRLOOD, a method that uses semantic role labeling to learn fine-grained local and global feature representations, achieving state-of-the-art performance on four benchmarks.
Identifying unexpected domain-shifted instances in natural language processing is crucial in real-world applications. Previous works identify the out-of-distribution (OOD) instance by leveraging a single global feature embedding to represent the sentence, which cannot characterize subtle OOD patterns well. Another major challenge current OOD methods face is learning effective low-dimensional sentence representations to identify the hard OOD instances that are semantically similar to the in-distribution (ID) data. In this paper, we propose a new unsupervised OOD detection method, namely Semantic Role Labeling Guided Out-of-distribution Detection (SRLOOD), that separates, extracts, and learns the semantic role labeling (SRL) guided fine-grained local feature representations from different arguments of a sentence and the global feature representations of the full sentence using a margin-based contrastive loss. A novel self-supervised approach is also introduced to enhance such global-local feature learning by predicting the SRL extracted role. The resulting model achieves SOTA performance on four OOD benchmarks, indicating the effectiveness of our approach. The code is publicly accessible via \url{https://github.com/cytai/SRLOOD}.