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 present LINGUIST, a method for generating annotated data for IntentClassification and Slot Tagging (IC+ST), via fine-tuning AlexaTM 5B, a5-billion-parameter multilingual sequence-to-sequence (seq2seq) model, on aflexible instruction prompt. In a 10-shot novel intent setting for the SNIPSdataset, LINGUIST surpasses state-of-the-art approaches (Back-Translation andExample Extrapolation) by a wide margin, showing absolute improvement for thetarget intents of +1.9 points on IC Recall and +2.5 points on ST F1 Score. Inthe zero-shot cross-lingual setting of the mATIS++ dataset, LINGUISTout-performs a strong baseline of Machine Translation with Slot Alignment by+4.14 points absolute on ST F1 Score across 6 languages, while matchingperformance on IC. Finally, we verify our results on an internal large-scalemultilingual dataset for conversational agent IC+ST and show significantimprovements over a baseline which uses Back-Translation, Paraphrasing and SlotCatalog Resampling. To our knowledge, we are the first to demonstrateinstruction fine-tuning of a large-scale seq2seq model to control the outputsof multilingual intent- and slot-labeled data generation.

LINGUIST: Language Model Instruction Tuning to Generate Annotated Utterances for Intent Classification and Slot Tagging