Expanding
Digital
Assyriology
with
Machine Learning
Émilie Pagé-Perron
University of Toronto
Leipzig, March 21st 2017
Outline
2
Global Philology Open Conference - February 2017
© Michel Royon / Wikimedia Commons
Way back CDLI
3
Global Philology Open Conference - February 2017
1998
2003
2010
4
Global Philology Open Conference - February 2017
http://cdli.ucla.edu
Access: Licenses and technical barriers
Restrictive licenses
Scraper required
5
Global Philology Open Conference - February 2017
CDLI in numbers
6
Global Philology Open Conference - February 2017
7
Global Philology Open Conference - February 2017
Encoding standards
8
Global Philology Open Conference - February 2017
CDLI-ATF
ORACC-ATF
Steve Tinney & Eleanor Robson, Oracc: The Open Richly Annotated Cuneiform Corpus
Challenges brought by encoding schemes
9
Global Philology Open Conference - February 2017
10
Nammu
11
Global Philology Open Conference - February 2017
Limitations in current methods
12
Global Philology Open Conference - February 2017
Statistical methods
13
Global Philology Open Conference - February 2017
Sara Brumfield 2013
14
Global Philology Open Conference - February 2017
Machine Translation and Automated Analysis of Cuneiform Languages (MTAAC)
University of Toronto Heather Baker (Assyriology)
Émilie Pagé-Perron (Assyriology)
UCLA Robert K. Englund (Assyriology)
Prashant Rajput (Comp. Sc.)
University of Frankfurt Christian Chiarcos (Comp ling.)
Maria Sukhareva (Comp ling.)
Ilya Khait (Assyriology)
15
Global Philology Open Conference - February 2017
Administrative accounts
16
Global Philology Open Conference - February 2017
NLP Pipeline
17
Global Philology Open Conference - February 2017
Ontologies
Adopted:
Potential:
18
Global Philology Open Conference - February 2017
"If Open Access is about removing barriers, Linked Open Data is about creating bridges."
Preservation and sustainability
19
Global Philology Open Conference - February 2017
International Backups
20
Global Philology Open Conference - February 2017
CDLI Framework Update Project "Phoenix"
21
Global Philology Open Conference - February 2017
Salient points
22
Global Philology Open Conference - February 2017
Thank you!
23
Global Philology Open Conference - February 2017
Contact
Émilie Pagé-Perron
Near and Middle Eastern Civilizations
University of Toronto
epageperron@gmail.com
@sohnyrin
CDLI
Robert K. Englund, UCLA, Director
Jürgen Renn, MPIWG, Co-Director
Jacob Dahl, University of Oxford, Co-PI
Bertrand Lafont, CNRS, Co-PI
Émilie Pagé-Perron, UofT, Co-PI
Collaborators
Christian Chiarcos, University of Frankfurt
Maria Sukhareva, University of Frankfurt
Ilya Khait, Berlin Free University