0

Why only Micro-F1? Class Weighting of Measures for Relation Classification

A new framework for weighting schemes in relation classification highlights model strengths and weaknesses by reporting results across different schemes, particularly useful for imbalanced datasets.

Year
2022
Venue
why-only-micro-f1-class-weighting-of-measures
Authors
4
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2205.09460ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

Relation classification models are conventionally evaluated using only a single measure, e.g., micro-F1, macro-F1 or AUC. In this work, we analyze weighting schemes, such as micro and macro, for imbalanced datasets. We introduce a framework for weighting schemes, where existing schemes are extremes, and two new intermediate schemes. We show that reporting results of different weighting schemes better highlights strengths and weaknesses of a model.

Authors

4