Few-Shot Learning for Issue Report Classification
Giuseppe Colavito, Filippo Lanubile, Nicole Novielli
Abstract
We describe our participation in the tool competition in the scope of the 2nd International Workshop on Natural Language-based Software Engineering. We propose a supervised approach relying on SETFIT, a framework for few-shot learning and sentence-BERT (SBERT), a variant of BERT for effective sentence embedding. We experimented with different settings, achieving the best performance by training and testing the SETFIT-based model on a subset of data with manually verified labels (Fl-micro <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$=.8321$</tex> ). For the sake of the challenge, we evaluate the SETFIT model on the challenge test set, achieving Fl-micro <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$=.7767$</tex> .