nl-uiuc AT lists.cs.illinois.edu
Subject: Natural language research announcements
List archive
- From: "Roth, Dan" <danr AT uiuc.edu>
- To: "nl-uiuc AT cs.uiuc.edu" <nl-uiuc AT cs.uiuc.edu>, "aivr AT cs.uiuc.edu" <aivr AT cs.uiuc.edu>, "dais AT cs.uiuc.edu" <dais AT cs.uiuc.edu>, "cogcomp AT cs.uiuc.edu" <cogcomp AT cs.uiuc.edu>, "vision AT cs.uiuc.edu" <vision AT cs.uiuc.edu>, "krr-group AT cs.uiuc.edu" <krr-group AT cs.uiuc.edu>, "group AT vision.ai.uiuc.edu" <group AT vision2.ai.uiuc.edu>
- Cc: cinda heeren <heeren AT cs.uiuc.edu>
- Subject: [nl-uiuc] FW: [dssifac] DSSI Speaker: James Clarke
- Date: Thu, 26 Jun 2008 11:11:22 -0500
- Accept-language: en-US
- Acceptlanguage: en-US
- List-archive: <http://lists.cs.uiuc.edu/pipermail/nl-uiuc>
- List-id: Natural language research announcements <nl-uiuc.cs.uiuc.edu>
From:
dssifac-bounces AT cs.uiuc.edu [mailto:dssifac-bounces AT cs.uiuc.edu] On Behalf Of cinda
heeren
Sent: Thursday, June 26, 2008
11:01 AM
To: lvantang AT usc.edu;
ruiyangwu AT gmail.com; Sharon M. Paradesi; yliu49 AT emory.edu; jxiao AT cs.utsa.edu;
cloverzj AT ksu.edu; Tim Weninger; xiajing AT ksu.edu; welshamy AT ksu.edu; Ashish
Panday; kjaeyeon AT iit.edu; nathanielryckman AT yahoo.com; zhourui AT ksu.edu;
caitlinl AT ksu.edu; sahenke AT gmail.com; shydslow AT aol.com; jen_nsims AT yahoo.com;
belljessicaf_05 AT yahoo.com; smartypantsizit AT yahoo.com; Donee' McAllister; William H. Hsu; Loeb, Alexander Thomas; Tim Vieira; Muriello, Daniel G; Robinson, Jacob C; Paul, Michael J; James
Clarke; dssifac AT cs.uiuc.edu; Sammons,
Mark
Subject: [dssifac] DSSI Speaker: James Clarke
Hi Everyone! It looks like we're continuing our pattern of Friday talks... (DSSI students, please plan to attend!) There will be a lunch following the talk in the usual spot (outside 2405 siebel).
Who: James Clarke, http://homepages.inf.ed.ac.uk/s0460084
When: 10:30a, Friday, 6/27
Where: Siebel 3405
What: Integer Linear Programming for NLP
Abstract:
Many natural language processing tasks, such as machine translation,
parsing and generation; require a decoding algorithm to find the best solution
for a given input and model. The decoding problem is also referred to as
the inference or search problem. Ideally during decoding we should find the
optimal solution in an efficient manner. However, many decoding
algorithms find sub-optimal solutions or force us to make strong assumptions of
conditional independence between variables. Formulating decoding as an
integer linear program allows us to infer globally optimal solutions and
enforce global constraints.
In this talk we give an introduction to the concepts, formulation and solving
of integer linear programs. We demonstrate how integer linear programming
can be used for decoding in two applications: sentence compression and
dependency parsing. Our approach can yield state-of-the-art or better
performance by introducing linguistically motivated constraints that allow us
to model the global properties observed in language.
dssifac mailing list
dssifac AT cs.uiuc.edu
http://lists.cs.uiuc.edu/mailman/listinfo/dssifac
- [nl-uiuc] FW: [dssifac] DSSI Speaker: James Clarke, Roth, Dan, 06/26/2008
Archive powered by MHonArc 2.6.16.