Summarizing Source Code using a Neural Attention Model
- Submitting institution
-
Heriot-Watt University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 24907298
- Type
- E - Conference contribution
- DOI
-
10.18653/v1/P16-1195
- Title of conference / published proceedings
- Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics : Long Papers
- First page
- 2073
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- August
- Year of publication
- 2016
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
-
- Citation count
- 61
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Originality: First Deep Learning model for generating a short textual summary starting from a snippet of source code, as well as two very large publicly available corpora for two programming languages (C# and SQL).
Significance: ACL is the top conference in Natural Language Processing (25% acceptance rate). Our datasets have since then become a benchmark in the Natural Language Processing research community that focuses on code-to-language.
Rigour: The neural latent representation of our model is able to successfully map long-range dependencies in the code to natural language, exceeding the performance of previous non-neural methods.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
