paper-with-me

홈 › Papers

Enhancing Out-of-Distribution Detection in Natural Language Understanding via Implicit Layer Ensemble

2022-10-20 · Hyunsoo Cho, Choonghyun Park, Jaewook Kang, Kang Min Yoo, Taeuk Kim, Sang-goo Lee

Out-of-distribution (OOD) detection aims to discern outliers from the intended data distribution, which is crucial to maintaining high reliability and a good user experience. Most recent studies in OOD detection utilize the information from a single representation that resides in the penultimate layer to determine whether the input is anomalous or not. Although such a method is straightforward, the potential of diverse information in the intermediate layers is overlooked. In this paper, we propose a novel framework based on contrastive learning that encourages intermediate features to learn layer-specialized representations and assembles them implicitly into a single representation to absorb rich information in the pre-trained language model. Extensive experiments in various intent classification and OOD datasets demonstrate that our approach is significantly more effective than other works.

📄 PDF Abstract BibTeX arXiv:2210.11034

Code (1)

hyunsoocho77/lacl-official 공식 구현 pytorch

Tasks

Contrastive Learningintent-classificationIntent ClassificationLanguage ModelingLanguage ModellingNatural Language UnderstandingOut-of-Distribution DetectionOut of Distribution (OOD) Detection

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

How Good Are LLMs at Out-of-Distribution Detection?

2023-08-20 · Bo Liu, LiMing Zhan, Zexin Lu, Yujie Feng 외

Out-of-distribution (OOD) detection plays a vital role in enhancing the reliability of machine learning (ML) models. The emergence of large language models (LLMs) has catalyzed a paradigm shift within the ML community, s…

Out-of-Distribution DetectionOut of Distribution (OOD) Detection

Enhancing Cross-lingual Natural Language Inference by Prompt-learning from Cross-lingual Templates

2022-05-01 · ACL 2022 5 · Kunxun Qi, Hai Wan, Jianfeng Du, Haolan Chen

Cross-lingual natural language inference (XNLI) is a fundamental task in cross-lingual natural language understanding. Recently this task is commonly addressed by pre-trained cross-lingual language models. Existing metho…

Cross-Lingual Natural Language InferenceCross-Lingual TransferLanguage ModelingLanguage Modelling+4

Enhancing Slot Tagging with Intent Features for Task Oriented Natural Language Understanding using BERT

2022-05-19 · Shruthi Hariharan, Vignesh Kumar Krishnamurthy, Utkarsh, Jayantha Gowda Sarapanahalli

Recent joint intent detection and slot tagging models have seen improved performance when compared to individual models. In many real-world datasets, the slot labels and values have a strong correlation with their intent…

Intent DetectionNatural Language Understanding

Semantic-Guided Natural Language and Visual Fusion for Cross-Modal Interaction Based on Tiny Object Detection

2025-11-07 · Xian-Hong Huang, Hui-Kai Su, Chi-Chia Sun, Jun-Wei Hsieh arxiv

This paper introduces a cutting-edge approach to cross-modal interaction for tiny object detection by combining semantic-guided natural language processing with advanced visual recognition backbones. The proposed method …

Natural Language UnderstandingObject Detection

Vision-Language Integration for Zero-Shot Scene Understanding in Real-World Environments

2025-10-29 · Manjunath Prasad Holenarasipura Rajiv, B. M. Vidyavathi arxiv

Zero-shot scene understanding in real-world settings presents major challenges due to the complexity and variability of natural scenes, where models must recognize new objects, actions, and contexts without prior labeled…

Scene UnderstandingActivity DetectionObject Recognition