Aspect-based Document Similarity for Research Papers

TL;DR

This paper introduces an aspect-based approach to research paper similarity using Transformer models, enabling more granular and aspect-aware recommendations, validated on large datasets with SciBERT performing best.

Contribution

It extends traditional similarity measures by incorporating aspect information via citation contexts and evaluates multiple Transformer models for this task.

Findings

SciBERT outperforms other models in aspect-based similarity

Large datasets of research paper pairs were used for evaluation

Aspect-aware similarity improves recommendation granularity

Abstract

Traditional document similarity measures provide a coarse-grained distinction between similar and dissimilar documents. Typically, they do not consider in what aspects two documents are similar. This limits the granularity of applications like recommender systems that rely on document similarity. In this paper, we extend similarity with aspect information by performing a pairwise document classification task. We evaluate our aspect-based document similarity for research papers. Paper citations indicate the aspect-based similarity, i.e., the section title in which a citation occurs acts as a label for the pair of citing and cited paper. We apply a series of Transformer models such as RoBERTa, ELECTRA, XLNet, and BERT variations and compare them to an LSTM baseline. We perform our experiments on two newly constructed datasets of 172,073 research paper pairs from the ACL Anthology and CORD-19 corpus. Our results show SciBERT as the best performing system. A qualitative examination validates our quantitative results. Our findings motivate future research of aspect-based document similarity and the development of a recommender system based on the evaluated techniques. We make our datasets, code, and trained models publicly available.