Figure 4 - uploaded by Alexander LeClair
Content may be subject to copyright.
Download
View publication
Boxplots of BLEU scores from attendgru for four runs under configurations for RQ1 and RQ2.

Boxplots of BLEU scores from attendgru for four runs under configurations for RQ1 and RQ2.

Source publication
Figure 1: Word count histogram for code, comment, and the book...
Figure 2: Histogram of word occurrences per document.
Figure 3: Overlap of words between methods and comments (areas a and...
Figure 4: Boxplots of BLEU scores from attendgru for four runs under...
Recommendations for Datasets for Source Code Summarization
Preprint
Full-text available
  • Apr 2019
Source Code Summarization is the task of writing short, natural language descriptions of source code. The main use for these descriptions is in software documentation e.g. the one-sentence Java method descriptions in JavaDocs. Code summarization is rapidly becoming a popular research problem, but progress is restrained due to a lack of suitable dat...
Cite
Download full-text

Contexts in source publication

Context 1
... observe a large "false" boost in BLEU score when split by function instead of split by project (see Figure 4). We consider this boost false because it involves placing functions from projects in the test set into the training set -an unrealistic scenario. ...
Context 2
... observe a large "false" boost in BLEU score when split by function instead of split by project (see Figure 4). We consider this boost false because it involves placing functions from projects in the test set into the training set -an unrealistic scenario. ...