21 March: DCLRS -- Mark Faulkner, Friday, March 24, 16:00 (TCD Lloyd Building
Dublin Computational Linguistics Research Seminar: Index of March 2017 | Dublin Computational Linguistics Research Seminar - Index of year: 2017 | Full index
Friday of this week (March 24), at 16:00, in the Lloyd Lecture Theatre
01 Theatre (TCD), Dr. Mark Faulkner (TCD, School of English) speaks
on:
Automating Language Profiling of Medieval Texts
Abstract:
Traditionally, linguistic analyses of medieval texts have been
conducted manually, with an expert reader working through a text and
sorting the linguistic forms it contains into relevant categories for
further analysis. It is on the basis of these analyses, often
conducted as late-nineteenth-century German doctoral dissertations,
that our understanding of the grammar of medieval English is built.
Recent decades have however seen the construction of numerous large
archives of medieval English texts, including the Dictionary of Old
English Corpus (c. 3 million words) and the Corpus of Middle English
Prose and Verse (c. 5 million words). These give the medievalist
access to a far greater range of data than the authors of the standard
grammars of medieval English had, and it is often (and probably
unsurprisingly) the case that when their generalisations are checked
against the corpora, they are found to be wrong. Yet for the moment
this checking is very laborious, as it must largely be conducted
manually.
This paper, from someone who is not a computational linguist but is
excited by the possibilities of applying computational methods to
medieval texts, demonstrates a number of the problems that arise from
trying to situate the language of one twelfth-century manuscript in
the context of medieval English. It delineates the processes involved
in tracing particular linguistic features in the manuscript and in the
corpora and identifies some of the repetitive aspects of this process
that might be automated. It does so in the hope that the expertise of
the audience will generate potential solutions that might be developed
in collaboration with the speaker.
ABOUT THE SPEAKER
Dr. Mark Faulkner was appointed as Ussher Assistant Professor in
Medieval Literature in September 2016, after four years at the
University of Sheffield. He has also taught at University College
Cork, Swansea University and the University of Oxford, where he
studied for his D. Phil. His research focuses on medieval literature
in its manuscript, historical and linguistic contexts, particularly in
the long twelfth century.
------
The Dublin Computational Linguistics Research Seminar series is a
cooperation among Trinity College Dublin, Dublin City University,
University College Dublin and the Dublin Institute of Technology, a
long standing collaboration which overlaps with the SFI CNGL/ADAPT
centres.
www.scss.tcd.ie/disciplines/intelligent_systems/clg/clg_web/DCLRS
Dublin Computational Linguistics Research Seminar - Index of March 2017 | Index of year: 2017 | Full index