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

Contextualized word embeddings have demonstrated state-of-the-art performancein various natural language processing tasks including those that concernhistorical semantic change. However, language models such as BERT was trainedprimarily on contemporary corpus data. To investigate whether training onhistorical corpus data improves diachronic semantic analysis, we present apre-trained BERT-based language model, HistBERT, trained on the balanced Corpusof Historical American English. We examine the effectiveness of our approach bycomparing the performance of the original BERT and that of HistBERT, and wereport promising results in word similarity and semantic shift analysis. Ourwork suggests that the effectiveness of contextual embeddings in diachronicsemantic analysis is dependent on the temporal profile of the input text andcare should be taken in applying this methodology to study historical semanticchange.

HistBERT: A Pre-trained Language Model for Diachronic Lexical Semantic Analysis