{"url":"/dataset/parallelcorpus-python","name":"ParallelCorpus-Python","full_name":null,"description_markdown":"The Python dataset introduced in the Parallel Corpus paper ([A Parallel Corpus of Python Functions and Documentation Strings for Automated Code Documentation and Code Generation](https://aclanthology.org/I17-2053.pdf)), commonly used for evaluating automated code summarization.","description_withheld":null,"homepage":"https://github.com/EdinburghNLP/code-docstring-corpus","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Source Code Summarization","url":"/task/code-summarization","datasets_with_task":"/datasets/task/code-summarization"},{"name":"Code Summarization","url":"/task/code-summarization-1","datasets_with_task":"/datasets/task/code-summarization-1"}],"languages":[],"variants":["ParallelCorpus-Python"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/source-code-summarization-on-parallelcorpus","task":"Source Code Summarization","dataset_variant":"ParallelCorpus-Python","rows":2,"metrics":["BLEU-4","METEOR"],"first_row_in_archive_order":{"model":"AdaMo-noise","paper":"/paper/assemble-foundation-models-for-automatic-code","metrics":{"BLEU-4":"34.05","METEOR":"21.92%"},"code_links":[{"title":"jianguda/afm4acs","url":"https://github.com/jianguda/afm4acs"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/assemble-foundation-models-for-automatic-code","title":"Assemble Foundation Models for Automatic Code Summarization","date":"2022-01-13","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}