Software Entity Recognition with Noise-Robust Learning

TL;DR

This paper introduces a noise-robust learning approach for software entity recognition that leverages a large Wikipedia-based lexicon and dataset, significantly improving recognition accuracy over existing methods.

Contribution

It develops a comprehensive software entity lexicon and dataset, and proposes self-regularization to enhance model robustness against noisy training data.

Findings

Models with self-regularization outperform vanilla models.

Significant improvements over state-of-the-art on benchmark datasets.

Public release of models, data, and code for future research.

Abstract

Recognizing software entities such as library names from free-form text is essential to enable many software engineering (SE) technologies, such as traceability link recovery, automated documentation, and API recommendation. While many approaches have been proposed to address this problem, they suffer from small entity vocabularies or noisy training data, hindering their ability to recognize software entities mentioned in sophisticated narratives. To address this challenge, we leverage the Wikipedia taxonomy to develop a comprehensive entity lexicon with 79K unique software entities in 12 fine-grained types, as well as a large labeled dataset of over 1.7M sentences. Then, we propose self-regularization, a noise-robust learning approach, to the training of our software entity recognition (SER) model by accounting for many dropouts. Results show that models trained with self-regularization outperform both their vanilla counterparts and state-of-the-art approaches on our Wikipedia benchmark and two Stack Overflow benchmarks. We release our models, data, and code for future research.