Exploring Ordinality in Text Classification: A Comparative Study of Explicit and Implicit Techniques

TL;DR

This paper compares explicit and implicit techniques for ordinal classification in NLP, analyzing their theoretical foundations and empirical performance to guide effective method selection.

Contribution

It provides a comprehensive comparison of explicit and implicit ordinal classification methods using PLMs, with strategic recommendations for different scenarios.

Findings

Explicit methods focus on label order through loss functions.

Implicit methods leverage semantic information in labels.

Recommendations vary based on task and data characteristics.

Abstract

Ordinal Classification (OC) is a widely encountered challenge in Natural Language Processing (NLP), with applications in various domains such as sentiment analysis, rating prediction, and more. Previous approaches to tackle OC have primarily focused on modifying existing or creating novel loss functions that \textbf{explicitly} account for the ordinal nature of labels. However, with the advent of Pretrained Language Models (PLMs), it became possible to tackle ordinality through the \textbf{implicit} semantics of the labels as well. This paper provides a comprehensive theoretical and empirical examination of both these approaches. Furthermore, we also offer strategic recommendations regarding the most effective approach to adopt based on specific settings.