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

Pre-trained language representation models (PLMs) cannot well capture factualknowledge from text. In contrast, knowledge embedding (KE) methods caneffectively represent the relational facts in knowledge graphs (KGs) withinformative entity embeddings, but conventional KE models cannot take fulladvantage of the abundant textual information. In this paper, we propose aunified model for Knowledge Embedding and Pre-trained LanguagE Representation(KEPLER), which can not only better integrate factual knowledge into PLMs butalso produce effective text-enhanced KE with the strong PLMs. In KEPLER, weencode textual entity descriptions with a PLM as their embeddings, and thenjointly optimize the KE and language modeling objectives. Experimental resultsshow that KEPLER achieves state-of-the-art performances on various NLP tasks,and also works remarkably well as an inductive KE model on KG link prediction.Furthermore, for pre-training and evaluating KEPLER, we construct Wikidata5M, alarge-scale KG dataset with aligned entity descriptions, and benchmarkstate-of-the-art KE methods on it. It shall serve as a new KE benchmark andfacilitate the research on large KG, inductive KE, and KG with text. The sourcecode can be obtained from https://github.com/THU-KEG/KEPLER.

KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation