CitePrompt: Using Prompts to Identify Citation Intent in Scientific Papers

TL;DR

CitePrompt introduces a prompt-based learning framework for classifying citation intent in scientific papers, achieving state-of-the-art results with less external information and effective few-shot and zero-shot performance.

Contribution

The paper presents a novel prompt-based approach for citation intent classification that outperforms existing methods and adapts well to limited labeled data scenarios.

Findings

State-of-the-art results on ACL-ARC dataset.

Significant improvement on SciCite dataset over baseline models.

Effective zero-shot and few-shot performance with high F1 scores.

Abstract

Citations in scientific papers not only help us trace the intellectual lineage but also are a useful indicator of the scientific significance of the work. Citation intents prove beneficial as they specify the role of the citation in a given context. In this paper, we present CitePrompt, a framework which uses the hitherto unexplored approach of prompt-based learning for citation intent classification. We argue that with the proper choice of the pretrained language model, the prompt template, and the prompt verbalizer, we can not only get results that are better than or comparable to those obtained with the state-of-the-art methods but also do it with much less exterior information about the scientific document. We report state-of-the-art results on the ACL-ARC dataset, and also show significant improvement on the SciCite dataset over all baseline models except one. As suitably large labelled datasets for citation intent classification can be quite hard to find, in a first, we propose the conversion of this task to the few-shot and zero-shot settings. For the ACL-ARC dataset, we report a 53.86% F1 score for the zero-shot setting, which improves to 63.61% and 66.99% for the 5-shot and 10-shot settings, respectively.