DeepAI AI Chat
Log In Sign Up

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

by   Jiashu Xu, et al.

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.


Summarization as Indirect Supervision for Relation Extraction

Relation extraction (RE) models have been challenged by their reliance o...

Improving Distantly Supervised Relation Extraction by Natural Language Inference

To reduce human annotations for relation extraction (RE) tasks, distantl...

STAD: Self-Training with Ambiguous Data for Low-Resource Relation Extraction

We present a simple yet effective self-training approach, named as STAD,...

Abstractified Multi-instance Learning (AMIL) for Biomedical Relation Extraction

Relation extraction in the biomedical domain is a challenging task due t...

A Distant Supervision Corpus for Extracting Biomedical Relationships Between Chemicals, Diseases and Genes

We introduce ChemDisGene, a new dataset for training and evaluating mult...

Estimation from Indirect Supervision with Linear Moments

In structured prediction problems where we have indirect supervision of ...

Deep Probabilistic Logic: A Unifying Framework for Indirect Supervision

Deep learning has emerged as a versatile tool for a wide range of NLP ta...