Learning for Semantic Parsing and Natural Language Generation Using Statistical Machine Translation

The Hong Kong University of Science and Technology
Department of Computer Science and Engineering
Human Language Technology Center

		JOINT SEMINAR
-----------------------------------------------------------------

Speaker:	Dr. Yuk Wah WONG
		Department of Computer Sciences
		University of Texas at Austin

Title:		"Learning for Semantic Parsing and Natural Language
		 Generation Using Statistical Machine Translation"

Date:		Monday, 17 September 2007

Time:		4:00pm - 5:00pm

Venue:		Lecture Theatre F
		(Leung Yat Sing Lecture Theatre, near lift nos. 25/26)
		The Hong Kong University of Science & Technology

Abstract:

One of the main goals of natural language processing (NLP) is to build
automated systems that can understand and generate human languages.  This
goal has so far remained elusive.  Existing hand-crafted systems can
provide in-depth analysis of domain sub-languages, but are often
notoriously fragile and costly to build.  Existing machine-learned systems
are considerably more robust, but are limited to relatively shallow NLP
tasks.

In this talk, we present novel statistical methods for robust natural
language understanding and generation.  We focus on two important
sub-tasks, semantic parsing and tactical generation.  The key idea is that
both tasks can be treated as the translation between natural languages and
formal meaning representation languages, and therefore, can be performed
using state-of-the-art statistical machine translation techniques.
Specifically, we employ synchronous parsing, which has been extensively
used in syntax-based machine translation, as the unifying framework for
semantic parsing and tactical generation.  The parsing and generation
algorithms learn all of their linguistic knowledge from annotated corpora,
and can handle natural-language sentences that are conceptually complex.
Experimental results in two real-world, restricted domains show that the
algorithms are more robust and accurate than the currently best systems
that require similar supervision.  Unlike previous systems that require
manually-constructed grammars and lexicons, our systems require much less
knowledge engineering and can be easily ported to other languages and
domains.

*******************
Biography:

Yuk Wah WONG has recently received his Ph.D. in Computer Sciences at the
University of Texas at Austin.  His advisor is Prof. Raymond J. Mooney.
He received his M.S. from the University of Texas at Austin in 2003, and
his B.Sc. from the University of Hong Kong in 2001. His research interests
include natural language understanding and generation, machine
translation, and information extraction.  He has been honored with the
Best Paper Award at the ACL-2007 conference in Prague for his work on
semantic parsing.