A Neural Few-Shot Text Classification Reality Check - Archive ouverte HAL Access content directly
Conference Papers Year :

A Neural Few-Shot Text Classification Reality Check

(1) , (1) , (1)
1

Abstract

Modern classification models tend to struggle when the amount of annotated data is scarce. To overcome this issue, several neural fewshot classification models have emerged, yielding significant progress over time, both in Computer Vision and Natural Language Processing. In the latter, such models used to rely on fixed word embeddings before the advent of transformers. Additionally, some models used in Computer Vision are yet to be tested in NLP applications. In this paper, we compare all these models, first adapting those made in the field of image processing to NLP, and second providing them access to transformers. We then test these models equipped with the same transformer-based encoder on the intent detection task, known for having a large number of classes. Our results reveal that while methods perform almost equally on the ARSC dataset, this is not the case for the Intent Detection task, where the most recent and supposedly best competitors perform worse than older and simpler ones (while all are given access to transformers). We also show that a simple baseline is surprisingly strong. All the new developed models, as well as the evaluation framework, are made publicly available 1 .
Fichier principal
Vignette du fichier
2021.eacl-main.79.pdf (397.06 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive

Dates and versions

ujm-03267869 , version 1 (22-06-2021)

Identifiers

  • HAL Id : ujm-03267869 , version 1

Cite

Thomas Dopierre, Christophe Gravier, Wilfried Logerais. A Neural Few-Shot Text Classification Reality Check. 16th Conference of the European Chapter of the Association for Computational Linguistics, Apr 2021, Kyiv (virtual), Ukraine. ⟨ujm-03267869⟩
19 View
26 Download

Share

Gmail Facebook Twitter LinkedIn More