The Fellowship of the Authors: Disambiguating Names from Social Network Context

TL;DR

This paper introduces a method for disambiguating names by leveraging social network context and graph-based clustering, outperforming traditional text-only approaches especially in domains with limited textual descriptions.

Contribution

It proposes a novel combination of BERT-based mention representations with graph induction and supervised clustering for name disambiguation, applicable to bibliographic and historical data.

Findings

Language model pretraining improves mention representations.

Bibliographic info enhances disambiguation performance.

Supervised clustering achieves competitive results with low computational cost.

Abstract

Most NLP approaches to entity linking and coreference resolution focus on retrieving similar mentions using sparse or dense text representations. The common "Wikification" task, for instance, retrieves candidate Wikipedia articles for each entity mention. For many domains, such as bibliographic citations, authority lists with extensive textual descriptions for each entity are lacking and ambiguous named entities mostly occur in the context of other named entities. Unlike prior work, therefore, we seek to leverage the information that can be gained from looking at association networks of individuals derived from textual evidence in order to disambiguate names. We combine BERT-based mention representations with a variety of graph induction strategies and experiment with supervised and unsupervised cluster inference methods. We experiment with data consisting of lists of names from two domains: bibliographic citations from CrossRef and chains of transmission (isnads) from classical Arabic histories. We find that in-domain language model pretraining can significantly improve mention representations, especially for larger corpora, and that the availability of bibliographic information, such as publication venue or title, can also increase performance on this task. We also present a novel supervised cluster inference model which gives competitive performance for little computational effort, making it ideal for situations where individuals must be identified without relying on an exhaustive authority list.