NADE: A Benchmark for Robust Adverse Drug Events Extraction in Face of Negations
Not on the map. Why?
Abstract (arXiv)
Adverse Drug Event (ADE) extraction models can rapidly examine large collections of social media texts, detecting mentions of drug-related adverse reactions and trigger medical investigations. However, despite the recent advances in NLP, it is currently unknown if such models are robust in face of negation, which is pervasive across language varieties. In this paper we evaluate three state-of-the-art systems, showing their fragility against negation, and then we introduce two possible strategies to increase the robustness of these models: a pipeline approach, relying on a specific component for negation detection; an augmentation of an ADE extraction dataset to artificially create negated samples and further train the models. We show that both strategies bring significant increases in performance, lowering the number of spurious entities predicted by the models. Our dataset and code will be publicly released to encourage research on the topic.
Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 7 of its 33 references that are in the map. First posted on arXiv 21 Sep 2021.
Builds on
7 of 33 references.
References · 7
- 2017Attention Is All You Needcited by 59,932
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2020Beyond Accuracy: Behavioral Testing of NLP models with CheckListcited by 979
- 2019SpanBERT: Improving Pre-training by Representing and Predicting Spanscited by 832
- 2019NegBERT: A Transfer Learning Approach for Negation Detection and Scope Resolutioncited by 36
- 2021Improving Adverse Drug Event Extraction with SpanBERT on Different Text Typologiescited by 7
- 2020Resolving the Scope of Speculation and Negation using Transformer-Based Architecturescited by 5
Built on by
Citing papers per year: 2022: 3; 2023: 1; 2024: 1.
5 papers.
- 2022Generalizing over Long Tail Concepts for Medical Term Normalizationcited by 8
- 2023Extensive Evaluation of Transformer-based Architectures for Adverse Drug Events Extractioncited by 4
- 2022Increasing Adverse Drug Events extraction robustness on social media: case study on negation and speculationcited by 3
- 2022Cross-lingual Approaches for the Detection of Adverse Drug Reactions in German from a Patient's Perspectivecited by 1
- 2024Evaluating the Robustness of Adverse Drug Event Classification Models Using Templatescited by 1
- 2024Evaluating the Robustness of Adverse Drug Event Classification Models Using Templates2 Jul 2024
- 2023Extensive Evaluation of Transformer-based Architectures for Adverse Drug Events Extraction8 Jun 2023
- 2022Generalizing over Long Tail Concepts for Medical Term Normalization21 Oct 2022
- 2022Increasing Adverse Drug Events extraction robustness on social media: case study on negation and speculation6 Sep 2022
- 2022Cross-lingual Approaches for the Detection of Adverse Drug Reactions in German from a Patient's Perspective3 Aug 2022