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

The development of deep neural networks has improved representation learningin various domains, including textual, graph structural, and relational triplerepresentations. This development opened the door to new relation extractionbeyond the traditional text-oriented relation extraction. However, research onthe effectiveness of considering multiple heterogeneous domain informationsimultaneously is still under exploration, and if a model can take an advantageof integrating heterogeneous information, it is expected to exhibit asignificant contribution to many problems in the world. This thesis works onDrug-Drug Interactions (DDIs) from the literature as a case study and realizesrelation extraction utilizing heterogeneous domain information. First, a deepneural relation extraction model is prepared and its attention mechanism isanalyzed. Next, a method to combine the drug molecular structure informationand drug description information to the input sentence information is proposed,and the effectiveness of utilizing drug molecular structures and drugdescriptions for the relation extraction task is shown. Then, in order tofurther exploit the heterogeneous information, drug-related items, such asprotein entries, medical terms and pathways are collected from multipleexisting databases and a new data set in the form of a knowledge graph (KG) isconstructed. A link prediction task on the constructed data set is conducted toobtain embedding representations of drugs that contain the heterogeneous domaininformation. Finally, a method that integrates the input sentence informationand the heterogeneous KG information is proposed. The proposed model is trainedand evaluated on a widely used data set, and as a result, it is shown thatutilizing heterogeneous domain information significantly improves theperformance of relation extraction from the literature.

Integrating Heterogeneous Domain Information into Relation Extraction: A Case Study on Drug-Drug Interaction Extraction