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

We introduce INSTRUCTOR, a new method for computing text embeddings giventask instructions: every text input is embedded together with instructionsexplaining the use case (e.g., task and domain descriptions). Unlike encodersfrom prior work that are more specialized, INSTRUCTOR is a single embedder thatcan generate text embeddings tailored to different downstream tasks anddomains, without any further training. We first annotate instructions for 330diverse tasks and train INSTRUCTOR on this multitask mixture with a contrastiveloss. We evaluate INSTRUCTOR on 70 embedding evaluation tasks (66 of which areunseen during training), ranging from classification and information retrievalto semantic textual similarity and text generation evaluation. INSTRUCTOR,while having an order of magnitude fewer parameters than the previous bestmodel, achieves state-of-the-art performance, with an average improvement of3.4% compared to the previous best results on the 70 diverse datasets. Ouranalysis suggests that INSTRUCTOR is robust to changes in instructions, andthat instruction finetuning mitigates the challenge of training a single modelon diverse datasets. Our model, code, and data are available athttps://instructor-embedding.github.io.

One Embedder, Any Task: Instruction-Finetuned Text Embeddings