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

arXiv:2404.03912v1 Announce Type: new
Abstract: 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 …

abstract application arxiv classification cs.ai cs.cl data dataset dictionary examples inference labels language language model languages low natural natural language nlp textual type zero-shot