Pointing to Subwords for Generating Function Names in Source Code
arXiv:2011.04241
Abstract
We tackle the task of automatically generating a function name from source code. Existing generators face difficulties in generating low-frequency or out-of-vocabulary subwords. In this paper, we propose two strategies for copying low-frequency or out-of-vocabulary subwords in inputs. Our best performing model showed an improvement over the conventional method in terms of our modified F1 and accuracy on the Java-small and Java-large datasets.
arXiv comment12 pages, accepted to COLING2020
References in corpus (7)
- Effective Approaches to Attention-based Neural Machine Translation
- Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond
- Structured Neural Summarization
- A Convolutional Attention Network for Extreme Summarization of Source Code
- Pointing the Unknown Words
- Modeling Vocabulary for Big Code Machine Learning
- A Neural Architecture for Generating Natural Language Descriptions from Source Code Changes