Detecting Statements in Text: A Domain-Agnostic Few-Shot Solution

arXiv:2405.05705v1 Announce Type: new
Abstract: Many tasks related to Computational Social Science and Web Content Analysis involve classifying pieces of text based on the claims they contain. State-of-the-art approaches usually involve fine-tuning models on large annotated datasets, which are costly to produce. In light of this, we propose and release a qualitative and versatile few-shot learning methodology as a common paradigm for any claim-based textual classification task. This methodology involves defining the classes as arbitrarily sophisticated taxonomies of claims, and …

abstract analysis art arxiv computational cs.cl datasets domain few-shot fine-tuning light release science social social science solution state tasks text type web