Mailing-List: contact java-user-help@lucene.apache.org; run by ezmlm
Precedence: bulk
Reply-To: java-user@lucene.apache.org
Received-SPF: pass (athena.apache.org: local policy)
From: "Provalov, Ivan" <Ivan.Provalov@cengage.com>
To: "java-user@lucene.apache.org" <java-user@lucene.apache.org>
Date: Fri, 6 May 2011 11:33:38 -0400
Subject: Michigan Information Retrieval Enthusiasts Group Quarterly Meetup -
 May 19th 2011
Thread-Topic: Michigan Information Retrieval Enthusiasts Group Quarterly
 Meetup - May 19th 2011
Thread-Index: AcwMAvi/L3b1GhzkRTCKwJDuH6S/IA==
Message-ID: <70EA5691BD59734784FF872CD1B9747A28501AD9B5@OHCINMBX01.corp.local>
Accept-Language: en-US
Content-Language: en-US
acceptlanguage: en-US
Content-Type: multipart/alternative;
	boundary="_000_70EA5691BD59734784FF872CD1B9747A28501AD9B5OHCINMBX01cor_"
MIME-Version: 1.0

--_000_70EA5691BD59734784FF872CD1B9747A28501AD9B5OHCINMBX01cor_
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable

Our next IR Meetup is at Cengage Learning on May 19, 2011.  Please RSVP her=
e:

http://www.meetup.com/Michigan-Information-Retrieval-Enthusiasts-Group/even=
ts/17567795/


Presentations:

1. Bayesian Language Model

This talk presents a Bayesian language model, originally described by (Teh =
2006), which uses a hierarchical Pitman-Yor process to describe the distrib=
ution of n-grams in an n-gram language model and which allows for a Bayesia=
n back-off and smoothing strategy. The language model, which assumes a powe=
r-law prior over the n-gram space, compares favorably with language models =
based upon state of the art empirical n-gram smoothing techniques. In addit=
ion to the language model, and primarily because the background information=
 required to understand it is somewhat difficult, that  material, most of w=
hich does not appear in (Teh 2006), is also presented in some detail. In pa=
rticular, background information related to the Dirichlet distribution and =
the Dirichlet process is given. The Dirichlet process is then related to th=
e Pitman-Yor process, and the hierarchical Pitman-Yor process is also prese=
nted.


2. Using GATE for Word Polarity in Context Classification

GATE (General Architecture for Text Engineering) is an open source software=
 for creating text processing workflows.  Core GATE includes the tools for =
solving many text engineering issues: modeling and persistence of specializ=
ed data structures; measurement, evaluation, benchmarking; visualization an=
d editing of annotations, ontologies, parse trees, etc.; extraction of trai=
ning instances for machine learning; pluggable machine learning implementat=
ions.  This tutorial will show how to use GATE for advanced machine learnin=
g applications.  Detecting word polarity in context will be used as an exam=
ple to show some of the GATE features.  The tutorial project is based on th=
e latest sentiment analysis research, specifically the work by Theresa Wils=
on, Janyce Wiebe, Paul Hoffmann "Recognizing Contextual Polarity: An Explor=
ation of Features for Phrase-Level Sentiment Analysis", 2009.  Using differ=
ent features (words, part of speech, negations, etc...) SVM classifier is t=
rained and evaluated.


Thank you,


Ivan Provalov


--_000_70EA5691BD59734784FF872CD1B9747A28501AD9B5OHCINMBX01cor_--