@inproceedings{sikder-kwegyir-afful-2026-syntactic,
title = "Do Syntactic Features Help Biomedical Relation Extraction? An Empirical Study of Verb Token and Dependency Graph Augmentation",
author = "Sikder, Mustafa and
Kwegyir-Afful, Ernest",
editor = "Demner-Fushman, Dina and
Ananiadou, Sophia and
Roberts, Kirk and
Tsujii, Junichi",
booktitle = "{B}io{NLP} 2026",
month = jul,
year = "2026",
address = "San Diego, California",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.bionlp-1.12/",
pages = "128--134",
ISBN = "979-8-89176-434-7",
abstract = "We investigate whether explicit syntactic features improve transformer-based biomedical relation extraction when added to typed entity marker pooling. We evaluate two augmentation strategies on top of BiomedBERT: (1) verb token augmentation, which concatenates the hidden state of the dependency root verb to the entity representations, and (2) a two-layer graph convolutional network (GCN) that refines encoder hidden states over the dependency parse before entity pooling. We experimented on three biomedical datasets: ChemProt, DDI, and AIMed with three random seeds. We found neither strategy consistently outperformed the entity-only baseline. The GCN yielded modest gains on AIMed (+0.007 F1) and ChemProt (+0.003 F1) but decreased performance on DDI (-0.013 F1). Verb token augmentation helps only on AIMed (+0.004 F1) and underperforms on the other two datasets. A syntactic characterization of the datasets reveals that DDI has substantially higher passive voice usage (50.7{\textbackslash}{\%} of relation-bearing sentences) than AIMed (27.0{\textbackslash}{\%}) or ChemProt (30.9{\textbackslash}{\%}), suggesting that syntactic augmentation is more effective when sentences exhibit active verbal structure with semantically informative predicates. These results suggest that corpus-level syntactic characteristics, particularly passive voice usage, may moderate the utility of explicit syntactic augmentation, though the small magnitude of observed differences warrants caution in interpretation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sikder-kwegyir-afful-2026-syntactic">
<titleInfo>
<title>Do Syntactic Features Help Biomedical Relation Extraction? An Empirical Study of Verb Token and Dependency Graph Augmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mustafa</namePart>
<namePart type="family">Sikder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ernest</namePart>
<namePart type="family">Kwegyir-Afful</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>BioNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-434-7</identifier>
</relatedItem>
<abstract>We investigate whether explicit syntactic features improve transformer-based biomedical relation extraction when added to typed entity marker pooling. We evaluate two augmentation strategies on top of BiomedBERT: (1) verb token augmentation, which concatenates the hidden state of the dependency root verb to the entity representations, and (2) a two-layer graph convolutional network (GCN) that refines encoder hidden states over the dependency parse before entity pooling. We experimented on three biomedical datasets: ChemProt, DDI, and AIMed with three random seeds. We found neither strategy consistently outperformed the entity-only baseline. The GCN yielded modest gains on AIMed (+0.007 F1) and ChemProt (+0.003 F1) but decreased performance on DDI (-0.013 F1). Verb token augmentation helps only on AIMed (+0.004 F1) and underperforms on the other two datasets. A syntactic characterization of the datasets reveals that DDI has substantially higher passive voice usage (50.7\textbackslash% of relation-bearing sentences) than AIMed (27.0\textbackslash%) or ChemProt (30.9\textbackslash%), suggesting that syntactic augmentation is more effective when sentences exhibit active verbal structure with semantically informative predicates. These results suggest that corpus-level syntactic characteristics, particularly passive voice usage, may moderate the utility of explicit syntactic augmentation, though the small magnitude of observed differences warrants caution in interpretation.</abstract>
<identifier type="citekey">sikder-kwegyir-afful-2026-syntactic</identifier>
<location>
<url>https://aclanthology.org/2026.bionlp-1.12/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>128</start>
<end>134</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Do Syntactic Features Help Biomedical Relation Extraction? An Empirical Study of Verb Token and Dependency Graph Augmentation
%A Sikder, Mustafa
%A Kwegyir-Afful, Ernest
%Y Demner-Fushman, Dina
%Y Ananiadou, Sophia
%Y Roberts, Kirk
%Y Tsujii, Junichi
%S BioNLP 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California
%@ 979-8-89176-434-7
%F sikder-kwegyir-afful-2026-syntactic
%X We investigate whether explicit syntactic features improve transformer-based biomedical relation extraction when added to typed entity marker pooling. We evaluate two augmentation strategies on top of BiomedBERT: (1) verb token augmentation, which concatenates the hidden state of the dependency root verb to the entity representations, and (2) a two-layer graph convolutional network (GCN) that refines encoder hidden states over the dependency parse before entity pooling. We experimented on three biomedical datasets: ChemProt, DDI, and AIMed with three random seeds. We found neither strategy consistently outperformed the entity-only baseline. The GCN yielded modest gains on AIMed (+0.007 F1) and ChemProt (+0.003 F1) but decreased performance on DDI (-0.013 F1). Verb token augmentation helps only on AIMed (+0.004 F1) and underperforms on the other two datasets. A syntactic characterization of the datasets reveals that DDI has substantially higher passive voice usage (50.7\textbackslash% of relation-bearing sentences) than AIMed (27.0\textbackslash%) or ChemProt (30.9\textbackslash%), suggesting that syntactic augmentation is more effective when sentences exhibit active verbal structure with semantically informative predicates. These results suggest that corpus-level syntactic characteristics, particularly passive voice usage, may moderate the utility of explicit syntactic augmentation, though the small magnitude of observed differences warrants caution in interpretation.
%U https://aclanthology.org/2026.bionlp-1.12/
%P 128-134
Markdown (Informal)
[Do Syntactic Features Help Biomedical Relation Extraction? An Empirical Study of Verb Token and Dependency Graph Augmentation](https://aclanthology.org/2026.bionlp-1.12/) (Sikder & Kwegyir-Afful, BioNLP 2026)
ACL