Indexing and Retrieving Natural Language Using Ternary Expressions

Indexing and Retrieving Natural Language Using Ternary Expressions (2001)

Cached

Download Links

[www.ai.mit.edu]

by Jimmy J. Lin

Venue:	MASTER’S THESIS, MIT
Citations:	12 - 3 self

Versions

Version History

Metadata Version 4

User correction supplied by SystemCorrections

Datum	Value	Source
TITLE	Indexing and Retrieving Natural Language Using Ternary Expressions	user correction - Legacy Corrections
AUTHOR NAME	Boris Katz	SVM HeaderParse 0.1
AUTHOR AFFIL	Expressions	SVM HeaderParse 0.2
AUTHOR NAME	Jimmy J. Lin	SVM HeaderParse 0.1
AUTHOR AFFIL	; Submitted to the Department of Electrical Engineering and Computer; MASSACHUSETTS INSTITUTE OF TECHNOLOGY	SVM HeaderParse 0.2
AUTHOR NAME	Jimmy J. Lin	SVM HeaderParse 0.1
AUTHOR AFFIL	; Submitted to the Department of Electrical Engineering and Computer; MASSACHUSETTS INSTITUTE OF TECHNOLOGY	SVM HeaderParse 0.2
ABSTRACT	Traditional information retrieval systems based on the "bag-of-words" paradigm cannot completely capture the semantic content of documents. Yet it is impossible with current technology to build a practical information access system that fully analyzes and understands unrestricted natural language. However, if we avoid the most complex and processing-intensive natural language understanding techniques, we can construct a large-scale information access system which is capable of processing unrestricted text, largely understanding it, and answering natural language queries with high precision. We believe that ternary expressions are the most suitable representational structure for such a system; they are expressive enough for information retrieval purposes, yet amenable to rapid large-scale indexing.	user correction - Legacy Corrections
YEAR	2001	INFERENCE
VENUE	Master’s thesis, MIT	INFERENCE
VENUE TYPE	TECHREPORT	INFERENCE
TECH	Master’s thesis	INFERENCE
CITATIONS	43 found	ParsCit 1.0