# Joint Entity Extraction and Assertion Detection for Clinical Text

arXiv: https://arxiv.org/abs/1812.05270 · HTML: https://mlsanity.com/paper/1812.05270/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Dec 2018.

## Built on by (most cited first, 6 of 6)

- [Wojood: Nested Arabic Named Entity Corpus and Recognition using BERT](https://mlsanity.com/paper/2205.09651/) (2022)
- [NEAR: Named Entity and Attribute Recognition of clinical concepts](https://mlsanity.com/paper/2208.13949/) (2022)
- [Neural Entity Recognition with Gazetteer based Fusion](https://mlsanity.com/paper/2105.13225/) (2021)
- [Beyond Negation Detection: Comprehensive Assertion Detection Models for Clinical NLP](https://mlsanity.com/paper/2503.17425/) (2025)
- [Scope resolution of predicted negation cues: A two-step neural network-based approach](https://mlsanity.com/paper/2109.07264/) (2021)
- [A Joint Neural Baseline for Concept, Assertion, and Relation Extraction from Clinical Text](https://mlsanity.com/paper/2603.07487/) (2026)

## Abstract (arXiv)

Negative medical findings are prevalent in clinical reports, yet discriminating them from positive findings remains a challenging task for information extraction. Most of the existing systems treat this task as a pipeline of two separate tasks, i.e., named entity recognition (NER) and rule-based negation detection. We consider this as a multi-task problem and present a novel end-to-end neural model to jointly extract entities and negations. We extend a standard hierarchical encoder-decoder NER model and first adopt a shared encoder followed by separate decoders for the two tasks. This architecture performs considerably better than the previous rule-based and machine learning-based systems. To overcome the problem of increased parameter size especially for low-resource settings, we propose the Conditional Softmax Shared Decoder architecture which achieves state-of-art results for NER and negation detection on the 2010 i2b2/VA challenge dataset and a proprietary de-identified clinical dataset.