Forget NLI, Use a Dictionary: Zero-Shot Topic Classification for Low-Resource Languages with Application to Luxembourgish

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Philippy, Fred, Haddadan, Shohreh, Guo, Siwen
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909161903620096
author Philippy, Fred
Haddadan, Shohreh
Guo, Siwen
author_facet Philippy, Fred
Haddadan, Shohreh
Guo, Siwen
contents In NLP, zero-shot classification (ZSC) is the task of assigning labels to textual data without any labeled examples for the target classes. A common method for ZSC is to fine-tune a language model on a Natural Language Inference (NLI) dataset and then use it to infer the entailment between the input document and the target labels. However, this approach faces certain challenges, particularly for languages with limited resources. In this paper, we propose an alternative solution that leverages dictionaries as a source of data for ZSC. We focus on Luxembourgish, a low-resource language spoken in Luxembourg, and construct two new topic relevance classification datasets based on a dictionary that provides various synonyms, word translations and example sentences. We evaluate the usability of our dataset and compare it with the NLI-based approach on two topic classification tasks in a zero-shot manner. Our results show that by using the dictionary-based dataset, the trained models outperform the ones following the NLI-based approach for ZSC. While we focus on a single low-resource language in this study, we believe that the efficacy of our approach can also transfer to other languages where such a dictionary is available.
format Preprint
id arxiv_https___arxiv_org_abs_2404_03912
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Forget NLI, Use a Dictionary: Zero-Shot Topic Classification for Low-Resource Languages with Application to Luxembourgish
Philippy, Fred
Haddadan, Shohreh
Guo, Siwen
Computation and Language
Artificial Intelligence
In NLP, zero-shot classification (ZSC) is the task of assigning labels to textual data without any labeled examples for the target classes. A common method for ZSC is to fine-tune a language model on a Natural Language Inference (NLI) dataset and then use it to infer the entailment between the input document and the target labels. However, this approach faces certain challenges, particularly for languages with limited resources. In this paper, we propose an alternative solution that leverages dictionaries as a source of data for ZSC. We focus on Luxembourgish, a low-resource language spoken in Luxembourg, and construct two new topic relevance classification datasets based on a dictionary that provides various synonyms, word translations and example sentences. We evaluate the usability of our dataset and compare it with the NLI-based approach on two topic classification tasks in a zero-shot manner. Our results show that by using the dictionary-based dataset, the trained models outperform the ones following the NLI-based approach for ZSC. While we focus on a single low-resource language in this study, we believe that the efficacy of our approach can also transfer to other languages where such a dictionary is available.
title Forget NLI, Use a Dictionary: Zero-Shot Topic Classification for Low-Resource Languages with Application to Luxembourgish
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2404.03912