English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recently many studies have been conducted on the topic of relationextraction. The DrugProt track at BioCreative VII provides a manually-annotatedcorpus for the purpose of the development and evaluation of relation extractionsystems, in which interactions between chemicals and genes are studied. Wedescribe the ensemble system that we used for our submission, which combinespredictions of fine-tuned bioBERT, sciBERT and const-bioBERT models by majorityvoting. We specifically tested the contribution of syntactic information torelation extraction with BERT. We observed that adding constituentbasedsyntactic information to BERT improved precision, but decreased recall, sincerelations rarely seen in the train set were less likely to be predicted by BERTmodels in which the syntactic information is infused. Our code is availableonline [https://github.com/Maple177/drugprot-relation-extraction].

Does constituency analysis enhance domain-specific pre-trained BERT models for relation extraction?