US2014237355A1PendingUtilityA1

Disambiguation of dependent referring expression in natural language processing

Assignee: IBMPriority: Feb 15, 2013Filed: Nov 26, 2013Published: Aug 21, 2014
Est. expiryFeb 15, 2033(~6.6 yrs left)· nominal 20-yr term from priority
G06F 40/253G06F 40/166G06F 40/247G06F 40/40G06F 40/289G06F 40/295G06F 17/24
53
PatentIndex Score
0
Cited by
0
References
0
Claims

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

exact text as granted — not AI-modified
What is claimed is: 
     
         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.

Join the waitlist — get patent alerts

Track US2014237355A1 — get alerts on status changes and closely related new filings.

We store only your email — no account needed. See our privacy policy.