Artificial Intelligence

“Automatic Reasoning for Inference-Based Natural Language Understanding”

When:
Wednesday, November 30, 2011, 3:00pm - 4:00pm PDTiCal
Where:
11th Floor Conf. Room (#1135)
Speaker:
Ekaterina Ovchinnikova
Description:

Abstract:
In order to understand a natural language expression it is usually not
enough to know the literal (“dictionary”) meaning of the words used in
this expression and compositional rules of the corresponding language.
Much more knowledge is involved in discourse processing; knowledge,
which may have nothing to do with the linguistic competence but is
rather related to our general conception of the world.
 
This talk discusses how knowledge-intensive natural language
understanding (NLU) can be modeled in a computational framework, with
a main focus on inference-based NLU. Two important components of each
inference-based NLU system are a knowledge base and an inference
machine.  In this talk, I will mainly focus on reasoning procedures
applicable to NLU. I will compare two main forms of logical inference:
deduction and abduction. Then I will present and discuss experiments
on Recognizing Textual Entailment, which is a knowledge-intensive NLU
task.
 
In the last part of the talk, I will present recent developments in
the framework of abductive reasoning as applied to NLU.
 
Biography:
Ekaterina Ovchinnikova studied mathematical, applied, and computational linguistics at the Universities of Saint-Petersburg (Russia) and Tübingen (Germany). During her studies and after obtaining a Master's degree she was working at the University of Tübingen (Germany) and participating in several computational linguistic projects. Later she moved to the University of Osnabrück (Germany).
 
In 2011, Ekaterina earned her doctor's degree in cognitive science from the Institute of Cognitive Science, University of Osnabrück (Germany). In her dissertation project, Ekaterina was focusing on inference-based natural language understanding.
 
Ekaterina's research interests include lexical semantics, ontologies, automatic reasoning, knowledge-intensive NLP tasks.
 
In 2010, Ekaterina was visiting ISI for 6 months and working with Jerry Hobbs on abductive reasoning for natural language understanding. Currently Ekaterina is visiting ISI for another 6 months.
 
Home Page:
http://cogsci.uni-osnabrueck.de/~eovchinn/

« Return to Events