<?xml version="1.0" encoding="utf-8"?>
<rss version="2.0"
	xmlns="http://backend.userland.com/rss2"
	xmlns:talks="http://z.cs.utexas.edu/users/ai-lab/talk/talksns.html#">
<channel>
<title>Forum for Artificial Intelligence</title>
<link>http://www.cs.utexas.edu/users/ai-lab/fai/</link>
<description>The Forum for Artificial Intelligence meets every other week (or so) to discuss scientific, philosophical, and cultural issues in artificial intelligence. Both technical research topics and broader inter-disciplinary aspects of AI are covered, and all are welcome to attend!</description>
<language>en-us</language>
<ttl>5</ttl>
<webMaster>doches@cs.utexas.edu</webMaster>
<pubDate>Wed, 14 May 08 12:00:00 CST</pubDate>
<item>
<title>Processing Code-Switched Text</title>
<link>http://www.cs.utexas.edu/users/ai-lab/fai/#May2</link>
<description><![CDATA[Code-switching is an interesting linguistic phenomenon commonly
observed in highly bilingual communities. It consists of mixing
languages in the same conversational event. Despite its popularity,
this type of discourse has received very little attention from the
natural language processing community. Most of the work in this area
attempts to solve problems where the language samples, either spoken
or written, are monolingual.

We recently started working on developing a part-of-speech tagger
for Spanish-English code-switched text. In the first half of this talk
I will discuss results of different approaches to solve the tagging
problem by taking advantage of existing resources for both
languages. The long-term goal of this research is to develop a full
syntactic parser for English-Spanish code-switched text, commonly
known as Spanglish, that can be exploited to tackle higher-level tasks
on mixed-language sources.  Although the work is focused on
English-Spanish bilingual discourse, the knowledge acquired from this
project can later be extended to other language combinations. In the
second half, I will discuss a related project aimed at exploiting our
bilingual tagger to develop an automated screening tool for the early
identification of Specific Language Impairment in Spanish-English
bilingual children.]]></description>
<pubDate>Wed, 14 May 08 12:57:30 CST</pubDate>
<talks:date>Friday, May 2</talks:date>
<talks:time>11:00am</talks:time>
<talks:location>ACES 2.402</talks:location>
<talks:speaker><a href="http://www.hlt.utdallas.edu/~tsolorio/">Thamar Solorio</a></talks:speaker>
<talks:institution>University of Texas at Dallas</talks:institution>
</item>
<item>
<title>Object Recognition by Scene Alignment</title>
<link>http://www.cs.utexas.edu/users/ai-lab/fai/#May23</link>
<description><![CDATA[Object detection and recognition is generally posed as a matching
problem between the object representation and the image features
(e.g., aligning pictorial cues, shape correspondence, constellations
of parts, etc.) while rejecting the background features using an
outlier process. In this work, we take a different approach: we
formulate the object detection problem as a problem of aligning
elements of the entire scene. The background, instead of being treated
as a set of outliers, is used to guide the detection process. Our
approach relies on the observation that when we have a big enough
database then we can find with high probability some images in the
database very close to a query image, as in similar scenes with
similar objects arranged in similar spatial configurations. If the
images in the retrieval set are partially labeled, then we can
transfer the knowledge of the labeling to the query image, and the
problem of object recognition becomes a problem of aligning scene
regions. But, can we find a dataset large enough to cover a large
number of scene configurations? Given an input image, how do we find a
good retrieval set, and, finally, how we do transfer the labels to the
input image? We will use two datasets; 1) the LabelMe dataset, which
contains more than 10,000 labeled images with over 180,000 annotated
objects. 2) The tiny images dataset: A dataset of weakly labeled
images with more than 79,000,000 images. We use this database to
perform object and scene classification, examining performance over a
range of semantic levels.

Work in collaboration with Rob Fergus, Bryan Russell, Ce Liu and
William T. Freeman

Additional information and links to relevant papers can be found
at: URL: http://people.csail.mit.edu/torralba/tinyimages/]]></description>
<pubDate>Wed, 14 May 08 12:57:30 CST</pubDate>
<talks:date>Friday, May 23</talks:date>
<talks:time>11:00am</talks:time>
<talks:location>ACES 2.402</talks:location>
<talks:speaker><a href="http://web.mit.edu/torralba/www/">Antonio Torralba</a></talks:speaker>
<talks:institution>Massachusetts Institute of Technology</talks:institution>
</item>
<item>
<title>Title TBA</title>
<link>http://www.cs.utexas.edu/users/ai-lab/fai/#Jun24</link>
<description><![CDATA[Abstract TBA]]></description>
<pubDate>Wed, 14 May 08 12:57:30 CST</pubDate>
<talks:date>Tuesday, June 24</talks:date>
<talks:time>11:00am</talks:time>
<talks:location>ACES 2.402</talks:location>
<talks:speaker><a href="http://www.cs.ualberta.ca/~sutton/">Rich Sutton</a></talks:speaker>
<talks:institution>University of Alberta</talks:institution>
</item>
</channel>
</rss>