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

Source code summarization aims to generate natural language descriptions ofcode snippets. Many existing studies learn the syntactic and semantic knowledgeof code snippets from their token sequences and Abstract Syntax Trees (ASTs).They use the learned code representations as input to code summarizationmodels, which can accordingly generate summaries describing source code.Traditional models traverse ASTs as sequences or split ASTs into paths asinput. However, the former loses the structural properties of ASTs, and thelatter destroys the overall structure of ASTs. Therefore, comprehensivelycapturing the structural features of ASTs in learning code representations forsource code summarization remains a challenging problem to be solved. In thispaper, we propose M2TS, a Multi-scale Multi-modal approach based on Transformerfor source code Summarization. M2TS uses a multi-scale AST feature extractionmethod, which can extract the structures of ASTs more completely and accuratelyat multiple local and global levels. To complement missing semantic informationin ASTs, we also obtain code token features, and further combine them with theextracted AST features using a cross modality fusion method that not only fusesthe syntactic and contextual semantic information of source code, but alsohighlights the key features of each modality. We conduct experiments on twoJava and one Python datasets, and the experimental results demonstrate thatM2TS outperforms current state-of-the-art methods. We release our code athttps://github.com/TranSMS/M2TS.

M2TS: Multi-Scale Multi-Modal Approach Based on Transformer for Source Code Summarization