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

Learning distributed sentence representations is one of the key challenges innatural language processing. Previous work demonstrated that a recurrent neuralnetwork (RNNs) based sentence encoder trained on a large collection ofannotated natural language inference data, is efficient in the transferlearning to facilitate other related tasks. In this paper, we show that jointlearning of multiple tasks results in better generalizable sentencerepresentations by conducting extensive experiments and analysis comparing themulti-task and single-task learned sentence encoders. The quantitative analysisusing auxiliary tasks show that multi-task learning helps to embed bettersemantic information in the sentence representations compared to single-tasklearning. In addition, we compare multi-task sentence encoders withcontextualized word representations and show that combining both of them canfurther boost the performance of transfer learning.

Multi-task Learning for Universal Sentence Embeddings: A Thorough Evaluation using Transfer and Auxiliary Tasks