# End-to-End Models for Chemical-Protein Interaction Extraction: Better Tokenization and Span-Based Pipeline Strategies

arXiv: https://arxiv.org/abs/2304.01344 · HTML: https://mlsanity.com/paper/2304.01344/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 29 references that are in the map.
- First posted on arXiv 3 Apr 2023.

## Builds on (most cited first, 15 of 15)

- [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)
- [Stanza: A Python Natural Language Processing Toolkit for Many Human Languages](https://mlsanity.com/paper/2003.07082/) (2020)
- [BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining](https://mlsanity.com/paper/2210.10341/) (2022)
- [Transfer Learning in Biomedical Natural Language Processing: An Evaluation of BERT and ELMo on Ten Benchmarking Datasets](https://mlsanity.com/paper/1906.05474/) (2019)
- [Matching the Blanks: Distributional Similarity for Relation Learning](https://mlsanity.com/paper/1906.03158/) (2019)
- [Entity, Relation, and Event Extraction with Contextualized Span Representations](https://mlsanity.com/paper/1909.03546/) (2019)
- [ScispaCy: Fast and Robust Models for Biomedical Natural Language Processing](https://mlsanity.com/paper/1902.07669/) (2019)
- [End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures](https://mlsanity.com/paper/1601.00770/) (2016)
- [BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing](https://mlsanity.com/paper/2206.15076/) (2022)
- [An End-to-end Model for Entity-level Relation Extraction using Multi-instance Learning](https://mlsanity.com/paper/2102.05980/) (2021)
- [Neural Metric Learning for Fast End-to-End Relation Extraction](https://mlsanity.com/paper/1905.07458/) (2019)
- [Abstractified Multi-instance Learning (AMIL) for Biomedical Relation Extraction](https://mlsanity.com/paper/2110.12501/) (2021)
- [Let's Stop Incorrect Comparisons in End-to-end Relation Extraction!](https://mlsanity.com/paper/2009.10684/) (2020)
- [Extracting Chemical-Protein Interactions via Calibrated Deep Neural Network and Self-training](https://mlsanity.com/paper/2011.02207/) (2020)

## Built on by (most cited first, 4 of 4)

- [Do LLMs Surpass Encoders for Biomedical NER?](https://mlsanity.com/paper/2504.00664/) (2025)
- [Comparison of pipeline, sequence-to-sequence, and GPT models for end-to-end relation extraction: experiments with the rare disease use-case](https://mlsanity.com/paper/2311.13729/) (2023)
- [A Benchmark for End-to-End Zero-Shot Biomedical Relation Extraction with LLMs: Experiments with OpenAI Models](https://mlsanity.com/paper/2504.04083/) (2025)
- [Relation Extraction with Instance-Adapted Predicate Descriptions](https://mlsanity.com/paper/2503.17799/) (2025)

## Abstract (arXiv)

End-to-end relation extraction (E2ERE) is an important task in information extraction, more so for biomedicine as scientific literature continues to grow exponentially. E2ERE typically involves identifying entities (or named entity recognition (NER)) and associated relations, while most RE tasks simply assume that the entities are provided upfront and end up performing relation classification. E2ERE is inherently more difficult than RE alone given the potential snowball effect of errors from NER leading to more errors in RE. A complex dataset in biomedical E2ERE is the ChemProt dataset (BioCreative VI, 2017) that identifies relations between chemical compounds and genes/proteins in scientific literature. ChemProt is included in all recent biomedical natural language processing benchmarks including BLUE, BLURB, and BigBio. However, its treatment in these benchmarks and in other separate efforts is typically not end-to-end, with few exceptions. In this effort, we employ a span-based pipeline approach to produce a new state-of-the-art E2ERE performance on the ChemProt dataset, resulting in > 4% improvement in F1-score over the prior best effort. Our results indicate that a straightforward fine-grained tokenization scheme helps span-based approaches excel in E2ERE, especially with regards to handling complex named entities. Our error analysis also identifies a few key failure modes in E2ERE for ChemProt.