Micha Elsner

Assistant Professor
Department of Linguistics
Ohio State University
Oxley 222E
Google voice/chat:
Oxley Hall
1712 Neil Ave
Columbus OH 43210

By appointment, or when office is open, or 2:30 Mon, 10am Thurs
Research Publications Talks Teaching Software/Resources Clippers: Computational Linguistics at OSU North American Computational Linguistics Olympiad (NACLO) 2015

I'm an assistant professor at OSU Linguistics, working on computational linguistics with the Clippers lab group. Before coming to Ohio State, I was a postdoctoral researcher at the University of Edinburgh, working with Sharon Goldwater. I got my Ph.D. from Brown University in 2011, advised by Eugene Charniak, with Mark Johnson and Regina Barzilay as committee members. At Brown, I worked in the Brown Laboratory for Linguistic Information Processing (BLLIP). I graduated from the University of Rochester in 2005 with degrees in Computer Science and Classics.

Research projects

Fictional narratives

I am interested in what distinguishes a story with a plot from a mere sequence of events. This work draws on my research on discourse coherence, but looks at much larger documents at a higher level. (See EACL-12 and the sentiment visualization tool developed by Robert Ang.)

Language acquisition

With Sharon Goldwater and Naomi Feldman, I am working on modeling how infants learn the lexicon and phonetics of their native language. We're also collaborating with Jacob Eisenstein (phonetics of dialects) and Frank Wood (inference in non-parametric models). (See EMNLP-17, ACL-12, EMNLP-13, and the syllabus for LING-8800; software is now available!)

Where's Wally

In collaboration with Alasdair Clarke and Hannah Rohde, I am looking at how visual perception affects production and perception of referring expressions. To do so, we are collecting and analyzing a corpus of descriptions of people in Where's Wally images (he's called Waldo in the USA!). (See CogSci-17, Frontiers-13 and slides for TTI Speech and Language Day 2013. WREC dataset is available for download.)

Local discourse coherence and chat disentanglement

My thesis work focused on discourse coherence-- the way a document or conversation is structured to provide context for new information. I constructed models looking at where and how entities (things in the world) are mentioned in a text. I also showed that these models can be used to disentangle the different threads of conversation going on in a crowded chat room. (See ACL 11 a and b, CL 10, ACL 08 a and b, NAACL 07, coherence toolkit software and Cambridge 2012 talk.)



Tech Reports

Talks and Presentations

Academic talks

Outreach talks

Presentations in this section are aimed at a general audience.


Regularly scheduled

These courses are typically available, although I may not be teaching them this term.


Seminar courses are unlikely to recur, at least without major changes.

Software and resources