The Person Index Challenge: Extraction of Persons from Messy, Short Texts

TL;DR

This paper investigates how effectively an unsupervised algorithm can create a structured person index from short, messy texts with varied and ambiguous name mentions, providing a formal problem definition, a baseline solution, and an evaluation strategy.

Contribution

It formalizes the person indexing problem in short texts, introduces a ground truth generation method, and presents a baseline unsupervised approach with an evaluation framework.

Findings

Baseline approach demonstrates initial feasibility

Evaluation strategy enables performance measurement

Open source code supports future research

Abstract

When persons are mentioned in texts with their first name, last name and/or middle names, there can be a high variation which of their names are used, how their names are ordered and if their names are abbreviated. If multiple persons are mentioned consecutively in very different ways, especially short texts can be perceived as "messy". Once ambiguous names occur, associations to persons may not be inferred correctly. Despite these eventualities, in this paper we ask how well an unsupervised algorithm can build a person index from short texts. We define a person index as a structured table that distinctly catalogs individuals by their names. First, we give a formal definition of the problem and describe a procedure to generate ground truth data for future evaluations. To give a first solution to this challenge, a baseline approach is implemented. By using our proposed evaluation strategy, we test the performance of the baseline and suggest further improvements. For future research the source code is publicly available.