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

Task-Oriented Parsing (TOP) enables conversational assistants to interpretuser commands expressed in natural language, transforming them into structuredoutputs that combine elements of both natural language and intent/slot tags.Recently, Large Language Models (LLMs) have achieved impressive performance insynthesizing computer programs based on a natural language prompt, mitigatingthe gap between natural language and structured programs. Our paper focuses onharnessing the capabilities of LLMs for semantic parsing tasks, addressing thefollowing three key research questions: 1) How can LLMs be effectively utilizedfor semantic parsing tasks? 2) What defines an effective prompt? and 3) How canLLM overcome the length constraint and streamline prompt design by includingall examples as prompts? We introduce k Nearest Neighbor In-ContextLearning(kNN-ICL), which simplifies prompt engineering by allowing it to bebuilt on top of any design strategy while providing access to all demoexamples. Extensive experiments show that: 1)Simple ICL without kNN search canachieve a comparable performance with strong supervised models on the TOPtasks, and 2) kNN-ICL significantly improves the comprehension of complexrequests by seamlessly integrating ICL with a nearest-neighbor approach.Notably, this enhancement is achieved without the need for additional data orspecialized prompts.

kNN-ICL: Compositional Task-Oriented Parsing Generalization with Nearest Neighbor In-Context Learning