paper-with-me

홈 › Papers

Can NLI Provide Proper Indirect Supervision for Low-resource Biomedical Relation Extraction?

2022-12-21 · Jiashu Xu, Mingyu Derek Ma, Muhao Chen

Two key obstacles in biomedical relation extraction (RE) are the scarcity of annotations and the prevalence of instances without explicitly pre-defined labels due to low annotation coverage. Existing approaches, which treat biomedical RE as a multi-class classification task, often result in poor generalization in low-resource settings and do not have the ability to make selective prediction on unknown cases but give a guess from seen relations, hindering the applicability of those approaches. We present NBR, which converts biomedical RE as natural language inference formulation through indirect supervision. By converting relations to natural language hypotheses, NBR is capable of exploiting semantic cues to alleviate annotation scarcity. By incorporating a ranking-based loss that implicitly calibrates abstinent instances, NBR learns a clearer decision boundary and is instructed to abstain on uncertain instances. Extensive experiments on three widely-used biomedical RE benchmarks, namely ChemProt, DDI and GAD, verify the effectiveness of NBR in both full-set and low-resource regimes. Our analysis demonstrates that indirect supervision benefits biomedical RE even when a domain gap exists, and combining NLI knowledge with biomedical knowledge leads to the best performance gains.

📄 PDF Abstract BibTeX arXiv:2212.10784

Code (1)

luka-group/NLI_as_Indirect_Supervision 공식 구현 pytorch

Tasks

Multi-class ClassificationNatural Language InferenceRelationRelation Extraction

Similar Papers 제목 키워드 기반

Deep Probabilistic Logic: A Unifying Framework for Indirect Supervision

2018-08-26 · EMNLP 2018 10 · Hai Wang, Hoifung Poon

Deep learning has emerged as a versatile tool for a wide range of NLP tasks, due to its superior capacity in representation learning. But its applicability is limited by the reliance on annotated examples, which are diff…

Reading ComprehensionRepresentation Learning

Multi-View Synergistic Learning with Vision-Language Adaption for Low-Resource Biomedical Image Classification

2026-04-27 · Xiaoliu Luo, Minxue Xiao, Ting Xie, Mengzhu Wang 외 arxiv

Accurate biomedical image classification under low-resource conditions remains challenging due to limited annotations, subtle inter-class visual differences, and complex disease semantics. While vision--language models o…

parameter-efficient fine-tuningRepresentation LearningContrastive LearningImage Classification

Concept Grounding to Multiple Knowledge Bases via Indirect Supervision

2016-01-01 · TACL 2016 1 · Chen-Tse Tsai, Dan Roth

We consider the problem of disambiguating concept mentions appearing in documents and grounding them in multiple knowledge bases, where each knowledge base addresses some aspects of the domain. This problem poses a few a…

Entity Linking

Summarization as Indirect Supervision for Relation Extraction

2022-05-19 · Keming Lu, I-Hung Hsu, Wenxuan Zhou, Mingyu Derek Ma 외

Relation extraction (RE) models have been challenged by their reliance on training data with expensive annotations. Considering that summarization tasks aim at acquiring concise expressions of synoptical information from…

RelationRelation ExtractionSentence

Creating Training Sets via Weak Indirect Supervision

2021-10-07 · ICLR 2022 4 · Jieyu Zhang, Bohan Wang, Xiangchen Song, Yujing Wang 외

Creating labeled training sets has become one of the major roadblocks in machine learning. To address this, recent \emph{Weak Supervision (WS)} frameworks synthesize training labels from multiple potentially noisy superv…

text-classificationText Classification