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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

In this paper, we consider the task of retrieving documents with predefinedtopics from an unlabeled document dataset using an unsupervised approach. Theproposed unsupervised approach requires only a small number of keywordsdescribing the respective topics and no labeled document. Existing approacheseither heavily relied on a large amount of additionally encoded world knowledgeor on term-document frequencies. Contrariwise, we introduce a method thatlearns jointly embedded document and word vectors solely from the unlabeleddocument dataset in order to find documents that are semantically similar tothe topics described by the keywords. The proposed method requires almost notext preprocessing but is simultaneously effective at retrieving relevantdocuments with high probability. When successively retrieving documents ondifferent predefined topics from publicly available and commonly used datasets,we achieved an average area under the receiver operating characteristic curvevalue of 0.95 on one dataset and 0.92 on another. Further, our method can beused for multiclass document classification, without the need to assign labelsto the dataset in advance. Compared with an unsupervised classificationbaseline, we increased F1 scores from 76.6 to 82.7 and from 61.0 to 75.1 on therespective datasets. For easy replication of our approach, we make thedeveloped Lbl2Vec code publicly available as a ready-to-use tool under the3-Clause BSD license.

Lbl2Vec: An Embedding-Based Approach for Unsupervised Document Retrieval on Predefined Topics