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

arXiv: https://arxiv.org/abs/2212.10784 · HTML: https://mlsanity.com/paper/2212.10784/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 70 references that are in the map.
- First posted on arXiv 21 Dec 2022.

## Builds on (most cited first, 30 of 41)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing](https://mlsanity.com/paper/2007.15779/) (2020)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [Zero-Shot Relation Extraction via Reading Comprehension](https://mlsanity.com/paper/1706.04115/) (2017)
- [Transfer Learning in Biomedical Natural Language Processing: An Evaluation of BERT and ELMo on Ten Benchmarking Datasets](https://mlsanity.com/paper/1906.05474/) (2019)
- [Selective Question Answering under Domain Shift](https://mlsanity.com/paper/2006.09462/) (2020)
- [PTR: Prompt Tuning with Rules for Text Classification](https://mlsanity.com/paper/2105.11259/) (2021)
- [LinkBERT: Pretraining Language Models with Document Links](https://mlsanity.com/paper/2203.15827/) (2022)
- [Generating Datasets with Pretrained Language Models](https://mlsanity.com/paper/2104.07540/) (2021)
- [Lessons from Natural Language Inference in the Clinical Domain](https://mlsanity.com/paper/1808.06752/) (2018)
- [Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling](https://mlsanity.com/paper/2010.11304/) (2020)
- [SciFive: a text-to-text transformer model for biomedical literature](https://mlsanity.com/paper/2106.03598/) (2021)
- [Entity-Relation Extraction as Multi-Turn Question Answering](https://mlsanity.com/paper/1905.05529/) (2019)
- [SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Models](https://mlsanity.com/paper/2203.02167/) (2022)
- [An Improved Baseline for Sentence-level Relation Extraction](https://mlsanity.com/paper/2102.01373/) (2021)
- [BioMegatron: Larger Biomedical Domain Language Model](https://mlsanity.com/paper/2010.06060/) (2020)
- [Learning from Context or Names? An Empirical Study on Neural Relation Extraction](https://mlsanity.com/paper/2010.01923/) (2020)
- [Label Verbalization and Entailment for Effective Zero- and Few-Shot Relation Extraction](https://mlsanity.com/paper/2109.03659/) (2021)
- [Fine-Tuning Large Neural Language Models for Biomedical Natural Language Processing](https://mlsanity.com/paper/2112.07869/) (2021)
- [Generating Data to Mitigate Spurious Correlations in Natural Language Inference Datasets](https://mlsanity.com/paper/2203.12942/) (2022)
- [Universal Natural Language Processing with Limited Annotations: Try Few-shot Textual Entailment as a Start](https://mlsanity.com/paper/2010.02584/) (2020)
- [Understanding Hard Negatives in Noise Contrastive Estimation](https://mlsanity.com/paper/2104.06245/) (2021)
- [Improving Biomedical Pretrained Language Models with Knowledge](https://mlsanity.com/paper/2104.10344/) (2021)
- [Read + Verify: Machine Reading Comprehension with Unanswerable Questions](https://mlsanity.com/paper/1808.05759/) (2018)
- [Summarization as Indirect Supervision for Relation Extraction](https://mlsanity.com/paper/2205.09837/) (2022)
- [Neural-Sim: Learning to Generate Training Data with NeRF](https://mlsanity.com/paper/2207.11368/) (2022)

## Built on by (most cited first, 13 of 13)

- [Parameter-Efficient Low-Resource Dialogue State Tracking by Prompt Tuning](https://mlsanity.com/paper/2301.10915/) (2023)
- [CliBench: A Multifaceted and Multigranular Evaluation of Large Language Models for Clinical Decision Making](https://mlsanity.com/paper/2406.09923/) (2024)
- [Memorize and Rank: Elevating Large Language Models for Clinical Diagnosis Prediction](https://mlsanity.com/paper/2501.17326/) (2025)
- [Improving Event Definition Following For Zero-Shot Event Detection](https://mlsanity.com/paper/2403.02586/) (2024)
- [STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language Models](https://mlsanity.com/paper/2305.15090/) (2023)
- [Dense Retrieval as Indirect Supervision for Large-space Decision Making](https://mlsanity.com/paper/2310.18619/) (2023)
- [Surveying the Dead Minds: Historical-Psychological Text Analysis with Contextualized Construct Representation (CCR) for Classical Chinese](https://mlsanity.com/paper/2403.00509/) (2024)
- [Event-Arguments Extraction Corpus and Modeling using BERT for Arabic](https://mlsanity.com/paper/2407.21153/) (2024)
- [MolCAP: Molecular Chemical reActivity pretraining and prompted-finetuning enhanced molecular representation learning](https://mlsanity.com/paper/2306.09187/) (2023)
- [Inferring from Logits: Exploring Best Practices for Decoding-Free Generative Candidate Selection](https://mlsanity.com/paper/2501.17338/) (2025)
- [WHERE and WHICH: Iterative Debate for Biomedical Synthetic Data Augmentation](https://mlsanity.com/paper/2503.23673/) (2025)
- [Entangled Relations: Leveraging NLI and Meta-analysis to Enhance Biomedical Relation Extraction](https://mlsanity.com/paper/2406.00226/) (2024)
- [EIoU-EMC: A Novel Loss for Domain-specific Nested Entity Recognition](https://mlsanity.com/paper/2504.14203/) (2025)

## Abstract (arXiv)

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.