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, neural networks have shown promising results for named entityrecognition (NER), which needs a number of labeled data to for model training.When meeting a new domain (target domain) for NER, there is no or a few labeleddata, which makes domain NER much more difficult. As NER has been researchedfor a long time, some similar domain already has well labelled data (sourcedomain). Therefore, in this paper, we focus on domain NER by studying how toutilize the labelled data from such similar source domain for the new targetdomain. We design a kernel function based instance transfer strategy by gettingsimilar labelled sentences from a source domain. Moreover, we propose anenhanced recurrent neural network (ERNN) by adding an additional layer thatcombines the source domain labelled data into traditional RNN structure.Comprehensive experiments are conducted on two datasets. The comparison resultsamong HMM, CRF and RNN show that RNN performs bette than others. When there isno labelled data in domain target, compared to directly using the source domainlabelled data without selecting transferred instances, our enhanced RNNapproach gets improvement from 0.8052 to 0.9328 in terms of F1 measure.

An Instance Transfer based Approach Using Enhanced Recurrent Neural Network for Domain Named Entity Recognition