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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Word embeddings have found their way into a wide range of natural languageprocessing tasks including those in the biomedical domain. While these vectorrepresentations successfully capture semantic and syntactic word relations,hidden patterns and trends in the data, they fail to offer interpretability.Interpretability is a key means to justification which is an integral part whenit comes to biomedical applications. We present an inclusive study oninterpretability of word embeddings in the medical domain, focusing on the roleof sparse methods. Qualitative and quantitative measurements and metrics forinterpretability of word vector representations are provided. For thequantitative evaluation, we introduce an extensive categorized dataset that canbe used to quantify interpretability based on category theory. Intrinsic andextrinsic evaluation of the studied methods are also presented. As for thelatter, we propose datasets which can be utilized for effective extrinsicevaluation of word vectors in the biomedical domain. Based on our experiments,it is seen that sparse word vectors show far more interpretability whilepreserving the performance of their original vectors in downstream tasks.

Evaluating Sparse Interpretable Word Embeddings for Biomedical Domain