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

Biomedical entity linking and event extraction are two crucial tasks tosupport text understanding and retrieval in the biomedical domain. These twotasks intrinsically benefit each other: entity linking disambiguates thebiomedical concepts by referring to external knowledge bases and the domainknowledge further provides additional clues to understand and extract thebiological processes, while event extraction identifies a key trigger andentities involved to describe each biological process which also captures thestructural context to better disambiguate the biomedical entities. However,previous research typically solves these two tasks separately or in a pipeline,leading to error propagation. What's more, it's even more challenging to solvethese two tasks together as there is no existing dataset that containsannotations for both tasks. To solve these challenges, we propose jointbiomedical entity linking and event extraction by regarding the eventstructures and entity references in knowledge bases as latent variables andupdating the two task-specific models in a hard Expectation-Maximization (EM)fashion: (1) predicting the missing variables for each partially annotateddataset based on the current two task-specific models, and (2) updating theparameters of each model on the corresponding pseudo completed dataset.Experimental results on two benchmark datasets: Genia 2011 for event extractionand BC4GO for entity linking, show that our joint framework significantlyimproves the model for each individual task and outperforms the strongbaselines for both tasks. We will make the code and model checkpoints publiclyavailable once the paper is accepted.

Iteratively Improving Biomedical Entity Linking and Event Extraction via Hard Expectation-Maximization