Browse by author
Lookup NU author(s): Stephen BonnerORCiD, Dr Stephen McGough
This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).
Text classification has long been a staple withinNatural Language Processing (NLP) with applications spanningacross diverse areas such as sentiment analysis, recommendersystems and spam detection. With such a powerful solution,it is often tempting to use it as the go-to tool for all NLPproblems since when you are holding a hammer, everythinglooks like a nail. However, we argue here that many taskswhich are currently addressed using classification are in factbeing shoehorned into a classification mould and that if weinstead address them as a ranking problem, we not only improvethe model, but we achieve better performance. We propose anovel end-to-end ranking approach consisting of a Transformernetwork responsible for producing representations for a pairof text sequences, which are in turn passed into a contextaggregating network outputting ranking scores used to determinean ordering to the sequences based on some notion of relevance.We perform numerous experiments on publicly-available datasetsand investigate the applications of ranking in problems oftensolved using classification. In an experiment on a heavily-skewed sentiment analysis dataset, converting ranking results toclassification labels yields an approximately 22% improvementover state-of-the-art text classification, demonstrating the efficacyof text ranking over text classification in certain scenarios.
Author(s): Amir Atapour-Abarghouei A, Bonner S, McGough AS
Publication type: Conference Proceedings (inc. Abstract)
Publication status: Published
Conference Name: IEEE International Conference on Big Data
Year of Conference: 2021
Pages: 3950-3959
Print publication date: 15/12/2021
Online publication date: 06/12/2021
Acceptance date: 01/11/2021
Date deposited: 24/01/2025
ISSN: 9781665445993
URL: https://doi.org/10.1109/BigData52589.2021.9671386
DOI: 10.1109/BigData52589.2021.9671386
