ProZe: Explainable and Prompt-guided Zero-Shot Text Classification - Archive ouverte HAL Access content directly
Journal Articles IEEE Internet Computing Year : 2022

ProZe: Explainable and Prompt-guided Zero-Shot Text Classification

Abstract

As technology accelerates the generation and communication of textual data, the need to automatically understand this content becomes a necessity. In order to classify text, being it for tagging, indexing or curating documents, one often relies on large, opaque models that are trained on pre-annotated datasets, making the process unexplainable, difficult to scale and ill-adapted for niche domains with scarce data. To tackle these challenges, we propose ProZe, a text classification approach that leverages knowledge from two sources: prompting pre-trained language models, as well as querying ConceptNet, a common-sense knowledge base which can be used to add a layer of explainability to the results. We evaluate our approach empirically and we show how this combination not only performs on par with state-of-the-art zero shot classification on several domains, but also offers explainable predictions that can be visualized.
No file

Dates and versions

hal-03684999 , version 1 (18-08-2022)

Identifiers

  • HAL Id : hal-03684999 , version 1

Cite

Ismail Harrando, Alison Reboud, Thomas Schleider, Thibault Ehrhart, Raphaël Troncy. ProZe: Explainable and Prompt-guided Zero-Shot Text Classification. IEEE Internet Computing, In press. ⟨hal-03684999⟩

Collections

EURECOM ANR
18 View
0 Download

Share

Gmail Mastodon Facebook X LinkedIn More