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

Neural Machine Translation (NMT) is widely applied in software engineeringtasks. The effectiveness of NMT for code retrieval relies on the ability tolearn from the sequence of tokens in the source language to the sequence oftokens in the target language. While NMT performs well in pseudocode-to-codetranslation, it might have challenges in learning to translate from naturallanguage query to source code in newly curated real-world code documentation/implementation datasets. In this work, we analyze the performance of NMT innatural language-to-code translation in the newly curated CAT benchmark thatincludes the optimized versions of three Java datasets TLCodeSum,CodeSearchNet, Funcom, and a Python dataset PCSD. Our evaluation shows that NMThas low accuracy, measured by CrystalBLEU and Meteor metrics in this task. Toalleviate the duty of NMT in learning complex representation of source code, wepropose ASTTrans Representation, a tailored representation of an AbstractSyntax Tree (AST) using a subset of non-terminal nodes. We show that theclassical approach NMT performs significantly better in learning ASTTransRepresentation over code tokens with up to 36% improvement on Meteor score.Moreover, we leverage ASTTrans Representation to conduct combined code searchprocesses from the state-of-the-art code search processes using GraphCodeBERTand UniXcoder. Our NMT models of learning ASTTrans Representation can boost theMean Reciprocal Rank of these state-of-the-art code search processes by up to3.08% and improve 23.08% of queries' results over the CAT benchmark.

Evaluating and Optimizing the Effectiveness of Neural Machine Translation in Supporting Code Retrieval Models: A Study on the CAT Benchmark