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

Relation classification is associated with many potential applications in theartificial intelligence area. Recent approaches usually leverage neuralnetworks based on structure features such as syntactic or dependency featuresto solve this problem. However, high-cost structure features make suchapproaches inconvenient to be directly used. In addition, structure featuresare probably domain-dependent. Therefore, this paper proposes a bi-directionallong-short-term-memory recurrent-neural-network (Bi-LSTM-RNN) model based onlow-cost sequence features to address relation classification. This modeldivides a sentence or text segment into five parts, namely two target entitiesand their three contexts. It learns the representations of entities and theircontexts, and uses them to classify relations. We evaluate our model on twostandard benchmark datasets in different domains, namely SemEval-2010 Task 8and BioNLP-ST 2016 Task BB3. In the former dataset, our model achievescomparable performance compared with other models using sequence features. Inthe latter dataset, our model obtains the third best results compared withother models in the official evaluation. Moreover, we find that the contextbetween two target entities plays the most important role in relationclassification. Furthermore, statistic experiments show that the contextbetween two target entities can be used as an approximate replacement of theshortest dependency path when dependency parsing is not used.

A Bi-LSTM-RNN Model for Relation Classification Using Low-Cost Sequence Features