Data augmentation strategies to improve text classification: a use case in smart cities.
Text classification is a very common and important task in Natural Language Processing. In many domains and real-world settings, a few labeled instances are the only resource available to train classifiers. Models trained on small datasets tend to overfit and produce inaccurate results – Data augmen...
| Published in: | Language Resources & Evaluation Vol. 58; no. 2; pp. 659 - 695 |
|---|---|
| Main Authors: | , |
| Format: | Article |
| Published: |
Springer Nature
Jun2024
|
| Subjects: | |
| Online Access: | View this record in EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=178064686&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 178064686 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 1574020X 179V jtl: Language Resources & Evaluation issn: 1574020X maglogo: N pubinfo: dt: Jun2024 vid: 58 iid: 2 pid: 237 pub: Springer Nature artinfo: ui: 178064686 10.1007/s10579-023-09685-w ppf: 659 ppct: 36 formats: fmt: – @attributes: type: T – @attributes: type: P size: 1.5MB tig: atl: Data augmentation strategies to improve text classification: a use case in smart cities. aug: au: Bencke, Luciana Moreira, Viviane Pereira affil: https://ror.org/041yk2d64 Institute of Informatics, Federal University of Rio Grande do Sul (UFRGS), Porto Alegre, Rio Gande do Sul, Brasil su: Data augmentation Smart cities Natural language processing Language models Classification algorithms sug: subj: Data augmentation Smart cities Natural language processing Language models Classification algorithms keyword: Low-resources Text classification ab: Text classification is a very common and important task in Natural Language Processing. In many domains and real-world settings, a few labeled instances are the only resource available to train classifiers. Models trained on small datasets tend to overfit and produce inaccurate results – Data augmentation (DA) techniques come as an alternative to minimize this problem. DA generates synthetic instances that can be fed to the classification algorithm during training. In this article, we explore a variety of DA methods, including back translation, paraphrasing, and text generation. We assess the impact of the DA methods over simulated low-data scenarios using well-known public datasets in English with classifiers built fine-tuning BERT models. We describe the means to adapt these DA methods to augment a small Portuguese dataset containing tweets labeled with smart city dimensions (e.g., transportation, energy, water, etc.). Our experiments showed that some classes were noticeably improved by DA – with an improvement of 43% in terms of F1 compared to the baseline with no augmentation. In a qualitative analysis, we observed that the DA methods were able to preserve the label but failed to preserve the semantics in some cases and that generative models were able to produce high-quality synthetic instances. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: Y custom: Language Resources & Evaluation is a copyright of Springer, 2024. All Rights Reserved. item: Language Resources & Evaluation holder: Springer Nature dt: @attributes: year: 2024 holdings: @attributes: islocal: N |
|---|