Domain-specific method for distinguishing type-denoting domain terms from entity-denoting domain terms

• US 10,073,833 B1
• Filed: 06/09/2017
• Issued: 09/11/2018
• Est. Priority Date: 03/09/2017
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Beller, Charles E., Chase, Jr., Paul J., Darden, Richard L., Drzewucki, Michael, Katz, Edward G., Phipps, Christopher, Ramirez, James E.
• Primary Examiner(s): Yen, Eric
• Application Number:
  US15/618,910
• Publication Number:
  US 20180260383A1
• Time in Patent Office: 459 Days
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/35 Clustering; Classification
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation

Abstract

Large lists of domain-specific terms are classified as a particular kind of linguistic object, e.g., lexical answer type T versus canonical answer E, based on features from a domain-specific corpus which have been found to distinguish between the linguistic objects. The distinguishing features can be identified in the corpus based on sets of the linguistic objects derived from question-and-answer pairs. A classifier can be trained using the distinguishing features, and the classification carried out using that classifier. The distinguishing features can include one or more syntactic features or one or more lexical features. The linguistic objects (the T and E training sets) can be extracted from the question-and-answer pairs automatically via text analysis if manually curated lists are not available. The classified terms can be included in a domain-specific lexicon which facilitates a deep question answering system to yield an answer to a question.

Claims

1. A method of distinguishing domain-specific terms from a list specific to a particular domain comprising:

extracting linguistic objects from a set of question-and-answer pairs wherein the linguistic objects include lexical answer types and answer entities, by executing first instructions in a computer system;

grouping the lexical answer types into a first set and grouping the answer entities into a second set, by executing second instructions in a computer system;

identifying distinguishing features of one or more corpora specific to the particular domain wherein the distinguishing features distinguish the lexical answer types in the first set from the answer entities in the second set, by executing third instructions in the computer system;

training a natural language classifier using the distinguishing features; and

classifying the domain-specific terms as either lexical answer type or answer entity based on the distinguishing features, by executing fourth instructions in the computer system, wherein said classifying uses the natural language classifier.

2. The method of claim 1 wherein the distinguishing features include one or more syntactic features.

3. The method of claim 1 wherein the distinguishing features include one or more lexical features.

4. The method of claim 1 wherein said extracting uses text analysis to automatically extract the linguistic objects.

5. The method of claim 1 further comprising applying a lexicon of classified terms to a deep question answering system to yield an answer to a question.