← Back to papers
2020 COLING COLING 2020

Pointing to Subwords for Generating Function Names in Source Code

Abstract

AbstractWe 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.

🌱 Topic Pioneer — Code Generation
🌉 Interdisciplinary Bridge — Deep Learning and Natural Language Processing
📈 Trend Setter — Code Generation
🧭 Keyword Pioneer — code tokenization
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Deep Learning, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Natural Language Processing, Reinforcement Learning, Speech & Audio

Authors

Shogo Fujita , Hidetaka Kamigaito , Hiroya Takamura , Manabu Okumura

Topics

Natural Language Processing > Applications > Code Generation Deep Learning > Learning Types > Code Generation

Keywords

copy mechanism code tokenization function name generation source code generation subword generation
Download PDF

Related papers

Persuasiveness of News Editorials depending on Ideology and Personality 2020
A Graph Representation of Semi-structured Data for Web Question Answering 2020
Span-based Joint Entity and Relation Extraction with Attention-based Span-specific and Contextual Semantic Representations 2020
Hierarchical Chinese Legal event extraction via Pedal Attention Mechanism 2020
End-to-End Emotion-Cause Pair Extraction with Graph Convolutional Network 2020