Semantic Role Labeling Guided Out-of-distribution Detection

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 pattern...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-03
Main Authors: Zou, Jinan, Guo, Maihao, Tian, Yu, Lin, Yuhao, Cao, Haiyao, Liu, Lingqiao, Abbasnejad, Ehsan, Shi, Javen Qinfeng
Format: Article
Language:English
Subjects:
Labeling
Natural language processing
Representations
Semantics
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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}.
ISSN:2331-8422