Microsoft Research and University of Washington
Date: Friday 11/1/2013
Time: 3:30-5PM
Place: Microsoft, Building 99, 1919
14820 NE 36th Street
Redmond, WA 98052
http://binged.it/14DwYYY
Come take advantage of this opportunity to connect with the computational
linguistics community at Microsoft and the University of Washington. This is
a regular opportunity for computational linguists at the University of
Washington and at Microsoft to discuss topics in the field and to connect in
a friendly informal atmosphere. We will have two talks (see below), followed
by informal mingling.
Woodley Packard and Emily M. Bender: Predicting the Scope of Negation using Minimal Recursion Semantics
Joint work with: Jonathon Read (Teesside University), Stephan Oepen
(University of Oslo & Potsdam University), Rebecca Dridan (University of
Oslo)
Abstract: Negation is a pervasive phenomenon in natural language, occurring in every
language and every genre. Despite the obviously profound impact of negation
on the meaning of a sentence, the most common approach to handling negation
in NLP systems is to ignore it, leading to all manner of (frequently)
comical errors. To encourage the exploration of better solutions, the 2012
*SEM Shared Task focused (among other things) on automatically identifying
negation and determining its scope. Several of the resulting systems were
quite successful, but despite the semantic nature of the task, the vast
majority of them were based on surface or syntactic methods.
In this talk, we will describe a semantics-based method of attacking the
same problem. Our system is based on the Minimal Recursion Semantics
structures produced by the English Resource Grammar, a broad-coverage,
precision, computational HPSG account of English. We show that it is
relatively straightforward to design high precision rules to determine what
portion of a sentence is within the scope of negation, by “crawling” through
these graphs. In a system combination with the winner of the 2012
competition, our method yields improved precision and F1. Moreover, our
“crawling” rules can be seen as a first-pass formalization of the shared
task annotation guidelines.
Author Bios:
Woodley Packard is currently a CLMS student at the University of Washington.
Since completing his M.S. and B.S. in Mathematics at Stanford University in
2006, he spent three years at a web technology startup, and has also spent
time at the University of Oslo in Norway. He is also the author of the ACE
parser-generator and various other experimental NLP tools.
Emily M. Bender is an Associate Professor of Linguistics and Adjunct
Associate Professor of Computer Science and Engineering at the University of
Washington. She is the Faculty Director of UW’s Professional Masters Program
in Computational Linguistics (CLMS). Her research interests center on
multilingual grammar engineering, computational semantics, and the
relationship between linguistics and computational linguistics. Her book,
_Linguistic Fundamentals for Natural Language Processing: 100 Essentials
from Morphology and Syntax_ appeared this year in Morgan & Claypool’s
Synthesis Lectures in Human Language Technologies.
Margaret Mitchell: Generating human reference to visible objects
everyday objects in real world settings, and discuss how to model this in a
generation system that produces humanlike descriptions. This talk will tie
in aspects of linguistics, cognitive science, and statistical natural
language processing.
Bio: Margaret Mitchell received her Master’s from the University of Washington’s
CLMA program and her PhD at the University of Aberdeen. She also spent
several years at Oregon Health and Science University as a visiting scholar.
Her research has recently focused on connecting vision to language.
