Salvato in:
Dettagli Bibliografici
Autori principali: Kasa, Siva Rajesh, Goel, Aniket, Gupta, Karan, Roychowdhury, Sumegh, Bhanushali, Anish, Pattisapu, Nikhil, Murthy, Prasanna Srinivasa
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2405.11775
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913356955254784
author Kasa, Siva Rajesh
Goel, Aniket
Gupta, Karan
Roychowdhury, Sumegh
Bhanushali, Anish
Pattisapu, Nikhil
Murthy, Prasanna Srinivasa
author_facet Kasa, Siva Rajesh
Goel, Aniket
Gupta, Karan
Roychowdhury, Sumegh
Bhanushali, Anish
Pattisapu, Nikhil
Murthy, Prasanna Srinivasa
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_11775
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Exploring Ordinality in Text Classification: A Comparative Study of Explicit and Implicit Techniques
Kasa, Siva Rajesh
Goel, Aniket
Gupta, Karan
Roychowdhury, Sumegh
Bhanushali, Anish
Pattisapu, Nikhil
Murthy, Prasanna Srinivasa
Computation and Language
Machine Learning
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.
title Exploring Ordinality in Text Classification: A Comparative Study of Explicit and Implicit Techniques
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2405.11775