Campus Event Calendar
Event Entry
What and Who
Distributional and pattern-based techniques for unsupervised expansion of semantic resources
Marco Pennacchiotti
Yahoo! Inc., Santa Clara
Talk
AG 1, AG 3, AG 4, AG 5, SWS, RG1, MMCI
Public Audience
English
Note: We use this to send email in the morning.
Date, Time and Location
Thursday, 12 March 2009
10:30
45 Minutes
E1 4
024
Saarbrücken
Abstract
Lexical-semantic resources, ranging from simple concept lists to frame semantic repositories, play a critical role in most Natural Language Processing (NLP) and Artificial Intelligence applications. These resources can be automatically extracted from texts, typically adopting either of the following two approaches: distributional and pattern-based. Even though these techniques have demonstrated to be independently quite successful in several tasks, a fruitful integration between the two is still missing.
In this talk I will describe two state of the art systems for information harvesting,implementing the above approaches: 'Espresso', a pattern-based system for extracting semantic relations; and a system for inducing lexical knowledge based on distributional techniques.
I will outline strengths and weaknesses of the two approaches, and describe the potential offered by the integration of the two methods in real NLP tasks, such Textual Entailment Recognition. I will also briefly introduce how the extraction process can be scaled to the Web, using new recently introduced computational paradigms based on large clusters of computers.
Contact
Conny Liegl
302-70150
--email hidden
passcode not visible
logged in users only
Conny Liegl, 03/09/2009 14:06 -- Created document.