Deep parsing in Watson

Authors:
M. C. McCord;J. W. Murdock;B. K. Boguraev
Affiliations:
IBM Research Division, Thomas J. Watson Research Center, Yorktown Heights, NY;IBM Research Division, Thomas J. Watson Research Center, Yorktown Heights, NY;IBM Research Division, Thomas J. Watson Research Center, Yorktown Heights, NY
Venue:
IBM Journal of Research and Development
Year:
2012

Citing 15
Cited 11

WordNet: a lexical database for English

Communications of the ACM
Slot grammars

Computational Linguistics
Accurate unlexicalized parsing

ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Heuristics for broad-coverage natural language parsing

HLT '93 Proceedings of the workshop on Human Language Technology
Verbnet: a broad-coverage, comprehensive verb lexicon

Verbnet: a broad-coverage, comprehensive verb lexicon
Head-Driven Statistical Models for Natural Language Parsing

Computational Linguistics
Coarse-to-fine n-best parsing and MaxEnt discriminative reranking

ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Introduction to "This is Watson"

IBM Journal of Research and Development
Question analysis: how watson reads a clue

IBM Journal of Research and Development
Automatic knowledge extraction from documents

IBM Journal of Research and Development
Finding needles in the haystack: search and candidate generation

IBM Journal of Research and Development
Typing candidate answers using type coercion

IBM Journal of Research and Development
Textual evidence gathering and analysis

IBM Journal of Research and Development
Relation extraction and scoring in DeepQA

IBM Journal of Research and Development
Structured data and inference in DeepQA

IBM Journal of Research and Development

Introduction to "This is Watson"

IBM Journal of Research and Development
Question analysis: how watson reads a clue

IBM Journal of Research and Development
Automatic knowledge extraction from documents

IBM Journal of Research and Development
Finding needles in the haystack: search and candidate generation

IBM Journal of Research and Development
Typing candidate answers using type coercion

IBM Journal of Research and Development
Textual evidence gathering and analysis

IBM Journal of Research and Development
Relation extraction and scoring in DeepQA

IBM Journal of Research and Development
Structured data and inference in DeepQA

IBM Journal of Research and Development
Fact-based question decomposition in DeepQA

IBM Journal of Research and Development
Making Watson fast

IBM Journal of Research and Development
Toward constructing evidence-based legal arguments using legal decision documents and machine learning

Proceedings of the Fourteenth International Conference on Artificial Intelligence and Law

Quantified Score

Hi-index	0.00

Visualization

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.