From Index Locorum to Citation Network: an Approavch to the Automatic Extraction of Canonical Reeferences and its Applications to the Study of Classical Texts

Student thesis: Doctoral ThesisDoctor of Philosophy


My research focusses on the automatic extraction of canonical references
from publications in Classics. Such references are the standard
way of citing classical texts and are found in great numbers throughout
monographs, journal articles and commentaries.
In chapters 1 and 2 I argue for the importance of canonical citations
and for the need to capture them automatically. Their importance and
function is to signal text passages that are studied and discussed, often
in relation to one another as can be seen in parallel passages found in
modern commentaries. Scholars in the field have long been exploiting
this kind of information by manually creating indexes of cited passages,
the so-called indices locorum. However, the challenge we now face is
find new ways of indexing and retrieving information contained in the
growing volume of digital archives and libraries.
Chapters 3 and 4 look at how this problem can be tackled by translating
the extraction of canonical citations into a computationally solvable
problem. The approach I developed consists of treating the extraction
of such citations as a problem of named entity extraction. This problem
can be solved with some degree of accuracy by applying and adapting
methods of Natural Language Processing. In this part of the dissertation
I discuss the implementation of this approach as a working prototype
and an evaluation of its performance.
Once canonical references have been extracted from texts, the web of
relations between documents that they create can be represented as a
network. This network can then be searched, manipulated, visualised
and analysed in various ways. In chapter 5 I focus specifically on how
this network can be leveraged to search through bodies of secondary
literature. Finally in chapter 6 I discuss how my work opens up new
research perspectives in terms of visualisation, analysis and the application
of such automatically extracted citation networks.
Date of Award2015
Original languageEnglish
Awarding Institution
  • King's College London
SupervisorJonathan Ginzburg (Supervisor), Shalom Lappin (Supervisor) & Willard McCarty (Supervisor)

Cite this