SymTax: Symbiotic Relationship and Taxonomy Fusion for Effective Citation Recommendation

TL;DR

SymTax is a novel citation recommendation system that integrates local and global context, taxonomy fusion, and symbiotic relationships, significantly improving recommendation accuracy over state-of-the-art methods.

Contribution

The paper introduces SymTax, a three-stage architecture that incorporates taxonomy embeddings in hyperbolic space and models symbiosis to enhance citation recommendation.

Findings

Achieves 26.66% and 39.25% improvements in Recall@5 on ACL-200 and RefSeer datasets.

Develops a large dataset ArSyTa with 8.27 million citation contexts.

Demonstrates the effectiveness of taxonomy fusion and symbiosis modeling through extensive experiments.

Abstract

Citing pertinent literature is pivotal to writing and reviewing a scientific document. Existing techniques mainly focus on the local context or the global context for recommending citations but fail to consider the actual human citation behaviour. We propose SymTax, a three-stage recommendation architecture that considers both the local and the global context, and additionally the taxonomical representations of query-candidate tuples and the Symbiosis prevailing amongst them. SymTax learns to embed the infused taxonomies in the hyperbolic space and uses hyperbolic separation as a latent feature to compute query-candidate similarity. We build a novel and large dataset ArSyTa containing 8.27 million citation contexts and describe the creation process in detail. We conduct extensive experiments and ablation studies to demonstrate the effectiveness and design choice of each module in our framework. Also, combinatorial analysis from our experiments shed light on the choice of language models (LMs) and fusion embedding, and the inclusion of section heading as a signal. Our proposed module that captures the symbiotic relationship solely leads to performance gains of 26.66% and 39.25% in Recall@5 w.r.t. SOTA on ACL-200 and RefSeer datasets, respectively. The complete framework yields a gain of 22.56% in Recall@5 wrt SOTA on our proposed dataset. The code and dataset are available at https://github.com/goyalkaraniit/SymTax