English

Identifying Semantically Difficult Samples to Improve Text Classification

Computation and Language 2023-02-14 v1 Artificial Intelligence

Abstract

In this paper, we investigate the effect of addressing difficult samples from a given text dataset on the downstream text classification task. We define difficult samples as being non-obvious cases for text classification by analysing them in the semantic embedding space; specifically - (i) semantically similar samples that belong to different classes and (ii) semantically dissimilar samples that belong to the same class. We propose a penalty function to measure the overall difficulty score of every sample in the dataset. We conduct exhaustive experiments on 13 standard datasets to show a consistent improvement of up to 9% and discuss qualitative results to show effectiveness of our approach in identifying difficult samples for a text classification model.

Keywords

Cite

@article{arxiv.2302.06155,
  title  = {Identifying Semantically Difficult Samples to Improve Text Classification},
  author = {Shashank Mujumdar and Stuti Mehta and Hima Patel and Suman Mitra},
  journal= {arXiv preprint arXiv:2302.06155},
  year   = {2023}
}
R2 v1 2026-06-28T08:38:27.531Z