Climate-NLI: A Model for Natural Language Inference and Zero-Shot Classification on Climate-Related Text

ACL 2024 Workshop ClimateNLP Submission29 Authors

Keywords: NLI, Climate Change, zero-shot classification

TL;DR: This paper proposes the Climate-NLI that leverages the power of NLI model to build a general-purpose NLP framework.

Abstract: Climate change is one of the most significant challenges of our era, necessitating innovative solutions across multiple fields. Advancements in Natural Language Processing (NLP) offer a promising pathway, particularly through the development of generalized models applicable to various tasks. Despite recent progress, current specialized NLP models excel in individual tasks but require substantial domain-specific training data and fail to generalize well to new scenarios. This paper introduces the Climate-NLI, an approach that utilizes Natural Language Inference (NLI) models to create a versatile NLP framework. Experiment results on 10 climate-related datasets show that our proposed model obtained comparable results to the models that have been fine-tuned on task-specific datasets. Our proposed model can significantly reduce the use of computational resources by training only one general model that can be applied to different tasks.

Archival Submission: arxival

Submission Number: 29