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

Measuring sentence semantic similarity using pre-trained language models suchas BERT generally yields unsatisfactory zero-shot performance, and one mainreason is ineffective token aggregation methods such as mean pooling. In thispaper, we demonstrate under a Bayesian framework that distance betweenprimitive statistics such as the mean of word embeddings are fundamentallyflawed for capturing sentence-level semantic similarity. To remedy this issue,we propose to learn a categorical variational autoencoder (VAE) based onoff-the-shelf pre-trained language models. We theoretically prove thatmeasuring the distance between the latent categorical mixtures, namelyLatte-Mix, can better reflect the true sentence semantic similarity. Inaddition, our Bayesian framework provides explanations for why models finetunedon labelled sentence pairs have better zero-shot performance. We alsoempirically demonstrate that these finetuned models could be further improvedby Latte-Mix. Our method not only yields the state-of-the-art zero-shotperformance on semantic similarity datasets such as STS, but also enjoy thebenefits of fast training and having small memory footprints.

Latte-Mix: Measuring Sentence Semantic Similarity with Latent Categorical Mixtures