Managing credibility for a question answering system

• US 9,886,480 B2
• Filed: 09/05/2014
• Issued: 02/06/2018
• Est. Priority Date: 07/29/2014
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bastide, Paul R., Broomhall, Matthew E., Loredo, Robert E., Lu, Fang
• Primary Examiner(s): BURKE, JEFF A
• Application Number:
  US14/478,061
• Publication Number:
  US 20160034565A1
• Time in Patent Office: 1,250 Days
• Field of Search: None
• CPC Class Codes: G06F 16/24522 Translation of natural language queries to structured queries
• CPC Class Codes: G06F 16/334 Query execution G06F16/335 takes precedence
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/95 Retrieval from the web
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]

Abstract

A method and system for managing credibility of a set of search results for a search query is disclosed. The method can include determining, by a natural language processing technique configured to analyze a portion of the set of search results and a portion of the search query, a credibility factor configured to indicate similarity to a subject matter of the search query. The method can also include establishing a relevance relationship between the credibility factor and source information of a first search result of the set of search results, wherein the source information is based on the credibility factor. The method may also include computing a credibility score for the first search result of the set of search results based on the relevance relationship between the credibility factor and the source information of the set of search results.

Claims

1. A system for managing credibility of a set of computer-generated search results for a user-input search query in an automated question answering system, the system comprising:

a determining module configured to determine, using a natural language processing technique configured to analyze at least a portion of the set of computer-generated search results and at least a portion of the user-input search query, at least one credibility factor configured to indicate similarity to a subject matter of the user-input search query, wherein determining the at least one credibility factor includes;

identifying, by the natural language processing technique, an origin location feature of the user-input search query, a first chronology feature of the user-input search query, and a first subject matter of the user-input search query;

a parsing module configured to parse the portion of the set of computer-generated search results and the user-input search query to determine a semantic feature, wherein the semantic feature is at least in part associated with word meaning, wherein the parsing module parses the portion of the set of computer-generated search results and the user-input search query to determine a syntactic feature, wherein the syntactic feature is at least in part associated with part-of-speech;

an establishing module configured to establish a relevance relationship between the at least one credibility factor and source information of a first search result of the set of computer-generated search results, wherein the source information is based on the at least one credibility factor, and wherein establishing the relevance relationship includes;

comparing metadata coupled with the source information to metadata coupled with the subject matter of the user-input search query;

extracting a correlation between an author feature from the first search result of the set of computer-generated search results and the origin location feature of the user-input search query, wherein the author feature includes one or more of a nationality, a cultural background, a subject area expertise, or a first language;

extracting a correlation between a chronology feature from the first search result of the set of computer-generated search results and the first chronology feature of the user-input search query, wherein the first chronology feature of the user-input search query includes one of a date, a version number, or an accumulated preparation temporal value, and wherein extracting the correlation between the first chronology feature of the user-input search query and the second chronology feature of the first search result includes determining that a recency score of the second chronology feature is within a recency range associated with the first chronology feature;

extracting a correlation between a set of subject matter milestones from the first search result of the set of computer-generated search results and the first subject matter of the user-input search query, wherein extracting the correlation between the set of subject matter milestones from the first search result of the set of computer-generated search results and the first subject matter of the user-input search query comprises determining that a recency score of the set of subject matter milestones is within a recency score of the set of subject matter milestones and the set of subject matter milestones of the first search result;

a computing module configured to compute, by a statistical credibility model, a credibility score for the first search result of the set of computer-generated search results based on the relevance relationship between the at least one credibility factor and the source information of the set of computer-generated search results, wherein the statistical credibility model includes probabilistic information for the source information;

a visualization processor configured to select a subset of the computer-generated search results and further configured to provide the selected subset of the computer-generated search results in a display area; and

a generating module configured to generate, based on the recency score of the set of subject milestones, a cluster graph to represent the correlation between the subject matter and the set of subject matter milestones.