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

APIs have intricate relations that can be described in text and representedas knowledge graphs to aid software engineering tasks. Existing relationextraction methods have limitations, such as limited API text corpus andaffected by the characteristics of the input text.To address these limitations,we propose utilizing large language models (LLMs) (e.g., GPT-3.5) as a neuralknowledge base for API relation inference. This approach leverages the entireWeb used to pre-train LLMs as a knowledge base and is insensitive to thecontext and complexity of input texts. To ensure accurate inference, we designour analytic flow as an AI Chain with three AI modules: API FQN Parser, APIKnowledge Extractor, and API Relation Decider. The accuracy of the API FQNparser and API Relation Decider module are 0.81 and 0.83, respectively. Usingthe generative capacity of the LLM and our approach's inference capability, weachieve an average F1 value of 0.76 under the three datasets, significantlyhigher than the state-of-the-art method's average F1 value of 0.40. Compared toCoT-based method, our AI Chain design improves the inference reliability by67%, and the AI-crowd-intelligence strategy enhances the robustness of ourapproach by 26%.

Let's Discover More API Relations: A Large Language Model-based AI Chain for Unsupervised API Relation Inference