Fig 3 - Adapting Neural Text Classification for Improved Software Categorization

F1 Score for code-only and code-description standard datasets. We observe a significant drop in performance from codedescription to code-only in all cases, though this drop was lower for nn+cd than nn+w. Best overall performer was nn+cd.

Go to figure page

Reference

Adapting Neural Text Classification for Improved Software Categorization - Scientific Figure on ResearchGate. Available from: https://www.researchgate.net/figure/F1-Score-for-code-only-and-code-description-standard-datasets-We-observe-a-significant_fig2_327940487 [accessed 9 Dec, 2023]

Caption

Fig. 3: F1 Score for code-only and code-description standard datasets. We observe a significant drop in performance from codedescription to code-only in all cases, though this drop was lower for nn+cd than nn+w. Best overall performer was nn+cd.

Embed code

<a href="https://www.researchgate.net/figure/F1-Score-for-code-only-and-code-description-standard-datasets-We-observe-a-significant_fig2_327940487"><img src="https://www.researchgate.net/profile/Alexander-Leclair/publication/327940487/figure/fig2/AS:725277764243457@1549931102473/F1-Score-for-code-only-and-code-description-standard-datasets-We-observe-a-significant.ppm" alt="F1 Score for code-only and code-description standard datasets. We observe a significant drop in performance from codedescription to code-only in all cases, though this drop was lower for nn+cd than nn+w. Best overall performer was nn+cd."/></a>