MF-Cite : Citation Intent Classification in Scientific Papers Based on Multi-Feature Fusion

Anonymous

TL;DR: This paper proposes the MF-Cite framework, a scientific text representation model that combines citation contextual feature, WordNet-based semantic feature and part-of-speech feature for citation intent classification.

Abstract: Citations are crucial in scientific works. Citation analysis techniques help in literature search, citation recommendation, scientific assessment and other research works. Citation intent classification has proved to be useful as an important branch of citation analysis techniques, which categorizes the role that citations play in research works. However, scientific papers usually contain words that are difficult to understand and semantically uncertain, while we find that the classification labels have a greater relationship with the part-of-speech properties of the words in the citation context. Therefore, in this work, we propose a scientific text classification model called MF-Cite that combines citation context feature, WordNet-based semantic feature, and part-of-speech feature. It fuses them for scientific text representation, enabling the model to enhance the understanding of specialized domain terms and accurately comprehend the grammatical information of sentences. Experiments show that our method achieves more favorable results on the ACL-ARC and SciCite datasets.

Paper Type: long

Research Area: Semantics: Sentence-level Semantics, Textual Inference and Other areas

Contribution Types: Model analysis & interpretability

Languages Studied: English