REAL-TIME SEMANTIC ANNOTATION SYSTEM AND THE METHOD OF CREATING ONTOLOGY DOCUMENTS ON THE FLY FROM NATURAL LANGUAGE STRING ENTERED BY USER

• US 20100114563A1
• Filed: 11/02/2009
• Published: 05/06/2010
• Est. Priority Date: 11/03/2008
• Status: Abandoned Application

• Current Assignee: Korea Advanced Institute of Science and Technology
• Original Assignee: Edward Kangsup Byun
• Inventors: Ahn, Jinhyun, Choi, Key-Sun, Jung, Jason J.
• Application Number:
  US12/610,882
• Publication Number:
  US 20100114563A1
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 16/367 Ontology
• CPC Class Codes: G06F 40/169 Annotation, e.g. comment data or footnotes
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

Disclosed herein are a real-time semantic annotation system and a method of converting user-entered natural language strings into semantically-readable knowledge structure documents using the system in real time. The real-time semantic annotation system includes a natural language character string input device for enabling a user to enter natural language character strings, a character string pattern triplet-mapping table for storing natural language character string patterns and their corresponding triplets, a triplet extraction device for converting the entered natural language character strings into triplets by analyzing and processing the entered natural language character strings using the pattern-triplet mapping table, an alternative word recommendation device for providing notification that a user should enter an alternative word, and a machine-readable document generation device for generating machine-readable documents from the triplets using a semantically-readable knowledge structure.

Claims

1. A real-time semantic annotation system, comprising:

a natural language character string input device for enabling a user to enter natural language character strings;

a character string pattern triplet-mapping table for storing natural language character string patterns and their corresponding triplets;

a triplet extraction device for converting the entered natural language character strings into triplets by analyzing and processing the entered natural language character strings using the pattern-triplet mapping table;

an alternative word recommendation device for providing notification that a user should enter an alternative word; and

a machine-readable document generation device for generating machine-readable documents from the triplets using a semantically-readable knowledge structure.

2. The real-time semantic annotation system as set forth in claim 1, wherein the natural language character string input device comprises an input device, such as a keyboard or a touch pad for enabling character strings to be entered, and an output device, such as a monitor for enabling the entered character strings to be visually checked or a sound output device for enabling the entered character strings to be audibly checked.

3. The real-time semantic annotation system as set forth in claim 1, wherein the character string pattern-triplet mapping table is configured such that ARG parts of the character string patterns have been replaced with ARGs of the triplets.

4. The real-time semantic annotation system as set forth in claim 1, wherein the character string pattern-triplet mapping table is configured to represent information to be entered using a symbol, such as “

*.”

5. The real-time semantic annotation system as set forth in claim 1, wherein the triplet extraction device records a history of a part of a triplet represented using a symbol, such as “

*”

, and fills the part with corresponding information when the information is entered.

6. The real-time semantic annotation system as set forth in claim 1, wherein the alternative word recommendation device is configured to notify a user of the alternative word so that the user can enter a word suitable for a semantically-readable knowledge structure.