SYSTEM AND METHOD FOR PROVIDING QUESTION AND ANSWERS WITH DEFERRED TYPE EVALUATION

• US 20090292687A1
• Filed: 05/23/2008
• Published: 11/26/2009
• Est. Priority Date: 05/23/2008
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Fan, James, Zadrozny, Wlodek W., Gondek, David C., Ferrucci, David
• Granted Patent: US 8,332,394 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 5/04 Inference or reasoning models

Abstract

A system, method and computer program product for conducting questions and answers with deferred type evaluation based on any corpus of data. The method includes processing a query including waiting until a “Type” (i.e. a descriptor) is determined AND a candidate answer is provided; the Type is not required as part of a predetermined ontology but is only a lexical/grammatical item. Then, a search is conducted to look (search) for evidence that the candidate answer has the required LAT (e.g., as determined by a matching function that can leverage a parser, a semantic interpreter and/or a simple pattern matcher). In another embodiment, it may be attempted to match the LAT to a known Ontological Type and then look for a candidate answer up in an appropriate knowledge-base, database, and the like determined by that type. Then, all the evidence from all the different ways to determine that the candidate answer has the expected lexical answer type (LAT) is combined and one or more answers are delivered to a user.

Claims

1. computer-implemented method of generating answers to questions based on any corpus of data comprising the steps of:

receiving an input query; and

performing an automated query analysis including determining the lexical answer type;

automatically computing candidate answers to the input query using said corpus of data;

computing one or more lexical types (LAT) for each candidate answer;

using an automated scoring function comparing candidate answer lexical types to the query LAT and producing a score for each candidate answer; and

,

returning one or more answers based on the produced scores for delivery to a user.

2. The computer-implemented method of claim 1, wherein an input query comprises a string, a string with context, or a string with context wherein the context includes another string or data structure.

3. The computer-implemented method of claim 1, wherein said computing a LAT includes implementing a detection rule for detecting said LAT in a question or a candidate answer.

4. The computer-implemented method of claim 1, wherein said computing a LAT includes implementing a parser and/or semantic interpreter.

5. The computer-implemented method of claim 1, wherein said step of utilizing an automated scoring function for producing a score for each candidate answer received includes:

matching the candidate against instances in the corpus or a knowledge base;

retrieving types associated with lose instances in the corpus or the knowledge base

matching LAT(s) with types and producing a score representing the degree of match

6. The computer-implemented method of claim 5, wherein the candidate answer type and LAT(s) comprise a lexical string, the matching is performed by using string matching.

7. The computer-implemented method of claim 5, wherein the candidate answer and LAT(s) comprise a lexical string or a set of strings, the matching including checking for one or more of synonym or hyponym relation between the LAT and a type.

8. The computer-implemented method of claim 1, wherein a type is a lexical item and is or is not part of a predetermined ontology.

9. The computer-implemented method as claimed in claim 1, further comprising:

providing a previously obtained candidate answer ranking function operating on a collection of correctly scored examples by applying machine learning technique to a corpus of scored matching LAT type pairs.

12. The system as claimed in claim 1, wherein the candidate answer type and LAT(s) comprise a lexical string, the matching is performed by using a matching means for string matching.

10. A system for generating answers to questions based on any corpus of data comprising:

query analysis means for receiving an input query and performing query context analysis function to break down said input query into query terms and determining the lexical answer type;

candidate answer generating means automatically computing candidate answers to the input query using said corpus of data, said generating means further computing one or more lexical types (LAT) for each candidate answer;

a plurality of scoring modules each for automatically scoring all candidate answers each using an automated scoring function for comparing candidate answer lexical types (LAT) to the query LAT and producing a score for each candidate answer; and

,

said plurality of scoring modules returning one or more answers based on the produced scores for delivery to a user.

11. The system as claimed in claim 10, wherein each said plurality of scoring modules includes utilizing an automated scoring function means for producing a score for each candidate answer received, said automated scoring function means includes:

matching the candidate against instances in the corpus or a knowledge base;

retrieving types associated with those instances in the corpus or the knowledge base; and

,

matching LAT(s) with types and producing a score representing the degree of match.

13. The system as claimed in claim 11, wherein the candidate answer and LAT(s) comprise a lexical string or a set of strings, said matching is performed using a matching means for checking for one of synonymy or hyponymy relation between the LAT and a type.

14. The system as claimed in claim 11, further comprising:

means for applying machine learning technique to a corpus of scored matching LAT type pairs to provide a candidate answer ranking function.

15. A program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine to perform method steps for generating answers to questions based on any corpus of data, said method steps including the steps of:

receiving an input query; and

performing an automated query analysis including determining the lexical answer type;

automatically computing candidate answers to the input query using said corpus of data;

computing one or more lexical types (LAT) for each candidate answer;

using an automated scoring function comparing candidate answer lexical types (LAT) to the query LAT and producing a score for each candidate answer; and

,

returning one or more answers based on the produced scores for delivery to a user.

16. The program storage device readable by a machine as claimed in claim 15, wherein said computing a LAT includes one of:

implementing a detection rule for detecting said LAT in a question or a candidate answer, or implementing a parser and/or semantic interpreter.

17. The program storage device readable by a machine as claimed in claim 16, wherein said step of utilizing an automated scoring function for producing a score for each candidate answer received includes:

matching the candidate against instances in the corpus or a knowledge base;

retrieving types associated with those instances in the said corpus or the knowledge base;

matching LAT(s) with types and producing a score representing the degree of match.

18. The program storage device readable by a machine of claim 17, wherein the candidate answer and LAT(s) comprise a lexical string, the matching is performed by using string matching.

19. The program storage device readable by a machine of claim 17, wherein the candidate answer type and LAT(s) comprise a lexical string or a set of strings, the matching including checking for one or more of synonym or hyponym relation between the LAT and a type.

20. A method of deploying a computer program product for generating answers to questions based on any corpus of data, wherein, when executed, the computer program performs the steps of:

receiving an input query; and

performing an automated query analysis including determining the lexical answer type;

automatically computing candidate answers to the input query using said corpus of data;

computing one or more lexical types (LAT) for each candidate answer;

using an automated scoring function comparing candidate answer lexical types (LAT) to the query LAT and producing a score for each candidate answer; and

,

returning one or more answers based on the produced scores for delivery to a user.

21. The method of deploying a computer program product as claimed in claim 20, wherein said step of utilizing an automated scoring function for producing a score for each candidate answer received includes:

matching the candidate against instances in the corpus or a knowledge base;

retrieving types associated with those instances in the said corpus or the knowledge base (KB);

matching LAT(s) with types and producing a score representing the degree of match.

22. The method of deploying a computer program product as claimed in claim 20, wherein said degree of match represents a degree to which a candidate answer is coerced to the LAT.

23. The method of deploying a computer program product as claimed in claim 20, wherein the candidate answer type and LAT(s) comprise a lexical string, the matching is performed by using string matching.

24. The method of deploying a computer program product as claimed in claim 20, wherein the candidate answer and LAT(s) comprise a lexical string or a set of strings, the matching including checking for one or more of synonym or hyponym relation between the LAT and a type.

25. The method of deploying a computer program product as claimed in claim 20, further comprising:

providing a candidate answer ranking function operating on a collection of correctly scored examples by applying machine learning technique to a corpus of scored matching LAT type pairs.