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

A variety of contextualised language models have been proposed in the NLPcommunity, which are trained on diverse corpora to produce numerous NeuralLanguage Models (NLMs). However, different NLMs have reported different levelsof performances in downstream NLP applications when used as textrepresentations. We propose a sentence-level meta-embedding learning methodthat takes independently trained contextualised word embedding models andlearns a sentence embedding that preserves the complementary strengths of theinput source NLMs. Our proposed method is unsupervised and is not tied to aparticular downstream task, which makes the learnt meta-embeddings in principleapplicable to different tasks that require sentence representations.Specifically, we first project the token-level embeddings obtained by theindividual NLMs and learn attention weights that indicate the contributions ofsource embeddings towards their token-level meta-embeddings. Next, we applymean and max pooling to produce sentence-level meta-embeddings from token-levelmeta-embeddings. Experimental results on semantic textual similarity benchmarksshow that our proposed unsupervised sentence-level meta-embedding methodoutperforms previously proposed sentence-level meta-embedding methods as wellas a supervised baseline.

Unsupervised Attention-based Sentence-Level Meta-Embeddings from Contextualised Language Models