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

Due to the development of pre-trained language models, automated codegeneration techniques have shown great promise in recent years. However, thegenerated code is difficult to meet the syntactic constraints of the targetlanguage, especially in the case of Turducken-style code, where declarativecode snippets are embedded within imperative programs. In this study, wesummarize the lack of syntactic constraints into three significant challenges:(1) the efficient representation of syntactic constraints, (2) the effectiveintegration of syntactic information, and (3) the scalable syntax-firstdecoding algorithm. To address these challenges, we propose a syntax-guidedmulti-task learning approach TurduckenGen. Specifically, we first explicitlyappend the type information to the code tokens to capture the representation ofsyntactic constraints. Then we formalize code generation with syntacticconstraint representation as an auxiliary task to enable the model to learn thesyntactic constraints of the code. Finally, the syntactically correct code isselected accurately from the multiple candidates with the help of the compilerfeedback. Extensive experiments and comprehensive analysis demonstrate theeffectiveness and general applicability of our approach after being comparedwith six state-of-the-art baselines on two Turducken-style code datasets.Finally, we conducted a human study and found the code quality generated by ourapproach is better than baselines in terms of code readability and semanticsimilarity.

A Syntax-Guided Multi-Task Learning Approach for Turducken-Style Code Generation