nl-uiuc AT lists.cs.illinois.edu

Subject: Natural language research announcements

List archive

[nl-uiuc] AIIS seminar: Jason Eisner Wed 24/06, 3pm SC 1304

From: "Hockenmaier, Julia" <juliahmr AT illinois.edu>
To: "aiis AT cs.uiuc.edu" <aiis AT cs.uiuc.edu>, "aistudents AT cs.uiuc.edu" <aistudents AT cs.uiuc.edu>, "Hasegawa-Johnson, Mark Allan" <jhasegaw AT illinois.edu>, "Girju, Corina R" <girju AT illinois.edu>, "Roth, Dan" <danr AT illinois.edu>, "Oh, Sewoong" <swoh AT illinois.edu>, Jerry DeJong <dejong AT cs.uiuc.edu>, "Peng, Jian" <jianpeng AT illinois.edu>, "Smaragdis, Paris" <paris AT illinois.edu>, "Sinha, Saurabh" <sinhas AT illinois.edu>, "Han, Jiawei" <hanj AT illinois.edu>, "Schwartz, Lane Oscar Bingaman" <lanes AT illinois.edu>, "Warnow, Tandy" <warnow AT illinois.edu>, "Zhai, Chengxiang" <czhai AT illinois.edu>, "Diesner, Jana" <jdiesner AT illinois.edu>, "Blake, Catherine" <clblake AT illinois.edu>, "nl-uiuc AT cs.uiuc.edu" <nl-uiuc AT cs.uiuc.edu>, "vision AT cs.uiuc.edu" <vision AT cs.uiuc.edu>
Cc: "Cheek, Dawn S" <dcheek AT illinois.edu>
Subject: [nl-uiuc] AIIS seminar: Jason Eisner Wed 24/06, 3pm SC 1304
Date: Thu, 18 Jun 2015 22:53:00 +0000
Accept-language: en-US
List-archive: <http://lists.cs.uiuc.edu/pipermail/nl-uiuc/>
List-id: Natural language research announcements <nl-uiuc.cs.uiuc.edu>

**NOTE THE UNUSUAL TIME AND LOCATION**

AIIS Seminar:

Graphical Models Over String-Valued Random Variables

Prof. Jason Eisner

Johns Hopkins University

Wednesday June 24th 2015, 3pm

Siebel Center 1304

Abstract:

Natural language processing must sometimes consider the internal structure of words, e.g., in order to understand or generate an unfamiliar word. Unfamiliar words are systematically related to familiar ones due to linguistic processes such as morphology, phonology, abbreviation, copying error, and historical change. (Similar problems arise in genomics.)

We will show how to build joint probability models over many strings. These models are capable of predicting unobserved strings, or predicting the relationships among observed strings. However, computing the predictions of these models can be computationally hard. We outline approximate algorithms based on Markov chain Monte Carlo, belief propagation, and dual decomposition. We give results on some NLP tasks.

Bio:

Jason Eisner is Professor of Computer Science at Johns Hopkins University. His goal is to develop the probabilistic modeling, inference, and learning techniques needed for a unified model of all kinds of linguistic structure. He has worked on computational approaches to phonology, morphology, syntax, and semantics, as well as applied problems such as information extraction and machine translation. He is also the lead designer of Dyna, a new declarative programming language that provides an infrastructure for AI research. He has received two school-wide awards for excellence in teaching.

If you would like to meet with the speaker, please email Julia Hockenmaier (juliahmr AT illinois.edu)

[nl-uiuc] AIIS seminar: Jason Eisner Wed 24/06, 3pm SC 1304, Hockenmaier, Julia, 06/18/2015