This paper appears in:
IBM Journal of Research and Development
Date of Publication:
May-June 2012
Author(s):
McCord, M. C.
IBM Research Division, Thomas J. Watson Research Center, Yorktown Heights, NY, USA
Murdock, J. W.
;
Boguraev, B. K.
Volume: 56,
Issue: 3.4
On Page(s):
3:1
-
3:15
Product Type:
Journals & Magazines
Abstract
Two deep parsing components, an English Slot Grammar (ESG) parser and a predicate-argument structure (PAS) builder, provide core linguistic analyses of both the questions and the text content used by IBM Watson™ to find and hypothesize answers. Specifically, these components are fundamental in question analysis, candidate generation, and analysis of passage evidence. As part of the Watson project, ESG was enhanced, and its performance on Jeopardy!™ questions and on established reference data was improved. PAS was built on top of ESG to support higher-level analytics. In this paper, we describe these components and illustrate how they are used in a pattern-based relation extraction component of Watson. We also provide quantitative results of evaluating the component-level performance of ESG parsing.
Note: The Institute of Electrical and Electronics Engineers, Incorporated is distributing this Article with permission of the International Business Machines Corporation (IBM) who is the exclusive owner. The recipient of this Article may not assign, sublicense, lease, rent or otherwise transfer, reproduce, prepare derivative works, publicly display or perform, or distribute the Article.
Index Terms
Index Terms are available to subscribers and IEEE members.
ISSN : 0018-8646
Digital Object Identifier : 10.1147/JRD.2012.2185409
Date of Current Version :
Tue Apr 03 00:00:00 EDT 2012
Issue Date :
May-June 2012
Sponsored by :
IBM
Available to subscribers and IEEE members.
Available to subscribers and IEEE members.
