DISAMBIGUATION OF DEPENDENT REFERRING EXPRESSION IN NATURAL LANGUAGE PROCESSING

• US 20140237355A1
• Filed: 11/26/2013
• Published: 08/21/2014
• Est. Priority Date: 02/15/2013
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Byron, Donna Karen, Pikovsky, Alexander, Seabolt, Edward E., Bufe, John P.
• Application Number:
  US14/090,152
• Publication Number:
  US 20140237355A1
• Time in Patent Office: Days
• US Class Current: 715/256
• CPC Class Codes: G06F 40/166 Editing, e.g. inserting or deleting
• CPC Class Codes: G06F 40/247 Thesauruses; Synonyms
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G06F 40/295 Named entity recognition
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30

Abstract

A method for disambiguation of dependent referring expression in natural language processing is provided in the illustrative embodiments. A portion of a document in a set of document is selected, the portion including a set of dependent referring expression instances. The portion is filtered to identify an instance from a set of dependent referring expression instances by using a linguistic characteristic of the instance, the instance of dependent referring expression referring to a full expression occurring in the set of documents. The full expression is located in one member document in the set of documents by locating where the dependent referring expression is defined to be a stand-in for the full expression. The instance is resolved using the full expression such that information about the full expression is available at a location of the instance.

Claims

1. A method for disambiguation of dependent referring expression in natural language processing, the method comprising:

selecting a portion of a document in a set of documents, the portion including a set of dependent referring expression instances;

filtering the portion to identify an instance from a set of dependent referring expression instances by using a linguistic characteristic of the instance, the instance of dependent referring expression referring to a full expression occurring in the set of documents;

locating the full expression in one member document in the set of documents by locating where the dependent referring expression is defined to be a stand-in for the full expression; and

resolving, using a processor and a memory, the instance using the full expression such that information about the full expression is available at a location of the instance.

2. The method of claim 1, further comprising:

outputting a second set of documents corresponding to the set of documents, wherein a document in the second set of document corresponds to the document in the set of documents, and wherein the document in the second set of documents includes a modified form of the instance responsive to the resolving.

3. The method of claim 1, wherein the resolving comprises:

replacing the instance with a copy of the full expression.

4. The method of claim 1, wherein the resolving comprises:

modifying the instance by adding data at a location of the instance, such that the data makes the information about the full expression accessible from the location of the instance.

5. The method of claim 4, further comprising:

modifying the document to produce a second document, wherein the second document includes a mapping between the instance and the full expression; and

linking the instance to the mapping using a link, wherein the link is usable to make the information about the full expression accessible from the location of the instance.

6. The method of claim 1, wherein the instance and the full expression appear in the same document in the set of documents.

7. The method of claim 1, wherein none of the documents in the set of documents is a generally purposed repository usable for translating a document not in the set of documents.

8. The method of claim 1, wherein the set of documents is configured for natural language processing of cumulative contents of the set of documents.

9. The method of claim 1, further comprising:

receiving the set of documents, wherein the receiving occurs before the set of documents are subjected to natural language processing.