Are All the Datasets in Benchmark Necessary? A Pilot Study of Dataset Evaluation for Text Classification

Anonymous

Paper Link: https://openreview.net/forum?id=_EZT1Q_0ZTq

Paper Type: Long paper (up to eight pages of content + unlimited references and appendices)

Abstract: In this paper, we ask the research question of whether all the datasets in the benchmark are necessary. We approach this by first characterizing the distinguishability of datasets when comparing different systems. Experiments on 9 datasets and 36 systems show that several existing benchmark datasets contribute little to discriminating top-scoring systems, while those less used datasets exhibit impressive discriminative power. We further, taking the text classification task as a case study, investigate the possibility of predicting dataset discrimination based on its properties (e.g., average sentence length). Our preliminary experiments promisingly show that given a sufficient number of training experimental records, a meaningful predictor can be learned to estimate dataset discrimination over unseen datasets. We released all datasets with features explored in this work on DataLab.

Presentation Mode: This paper will be presented virtually

Virtual Presentation Timezone: UTC-8

Copyright Consent Signature (type Name Or NA If Not Transferrable): Jinlan Fu

Copyright Consent Name And Address: Organization: National University of Singapore; Address: 3 Research Link, Innovation 4.0, Singapore 117602