@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://preview.aclanthology.org/ingest-acl-workshops/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."
}