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

One of the long-standing challenges in lexical semantics consists in learningrepresentations of words which reflect their semantic properties. Theremarkable success of word embeddings for this purpose suggests thathigh-quality representations can be obtained by summarizing the sentencecontexts of word mentions. In this paper, we propose a method for learning wordrepresentations that follows this basic strategy, but differs from standardword embeddings in two important ways. First, we take advantage ofcontextualized language models (CLMs) rather than bags of word vectors toencode contexts. Second, rather than learning a word vector directly, we use atopic model to partition the contexts in which words appear, and then learndifferent topic-specific vectors for each word. Finally, we use a task-specificsupervision signal to make a soft selection of the resulting vectors. We showthat this simple strategy leads to high-quality word vectors, which are morepredictive of semantic properties than word embeddings and existing CLM-basedstrategies.

Deriving Word Vectors from Contextualized Language Models using Topic-Aware Mention Selection