Computational study of linguistic differences
This seminar focuses on computational methods for studying language change and variation. Languages differ based on time, geography, speakers (or author), or even audience. This course is concerned with how to find these differences, how to reason about them, and how to deal with them in computational linguistic methods and applications. In this course, we will read and discuss a selection of articles mainly in the areas of computational study of dialectology (dialectometry) and computational study of literary style, or stylometry, but also in other relevant areas of language change and variation depending on the participants’ interests.
See the course syllabus for more information.
Course plan
Date | Paper(s) / Subject | Slides / material |
---|---|---|
Nov 11 | Tutorial session with Gabmap and Stylo R . | instructions |
Nov 18 |
Eisenstein, O’Connor, Smith, and Xing (2010)
Grieve (2007) |
slides
slides |
Nov 25 |
Noecker, Ryan, and Juola (2013)
Dahllöf (2012) |
|
Dec 2 |
Garrard, Maloney, Hodges, and Patterson (2005)
Le, Lancashire, Hirst, and Jokel (2011) |
slides |
Dec 9 | No class | |
Dec 16 |
Clough and Stevenson (2011)
Bär, Zesch, and Gurevych (2012) |
slides
slides |
Jan 13 |
Can and Patton (2004)
Pennebaker and Stone (2003) |
|
Jan 20 |
Ramirez-Esparza, Chung, Kacewicz, and Pennebaker (2008)
Windram, Shaw, Robinson, and Howe (2008) |
|
Jan 27 |
Leinonen (2011)
Ilisei, Inkpen, Pastor, and Mitkov (2010) |
slides |
Feb 3 | Zechner, Muhr, Kern, and Granitzer (2009) | |
Feb 10 | Hands-on exercises | instructions |