The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Jul. 04, 2017

Filed:

Jan. 23, 2013
Applicant:

National Institute of Information and Communications Technology, Tokyo, JP;

Inventors:

Jonghoon Oh, Tokyo, JP;

Kentaro Torisawa, Tokyo, JP;

Chikara Hashimoto, Tokyo, JP;

Takuya Kawada, Tokyo, JP;

Stijn De Saeger, Tokyo, JP;

Junichi Kazama, Tokyo, JP;

Yiou Wang, Tokyo, JP;

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06F 15/18 (2006.01); G06N 99/00 (2010.01); G06F 17/30 (2006.01); G06F 17/27 (2006.01); G06N 7/00 (2006.01);
U.S. Cl.
CPC ...
G06N 99/005 (2013.01); G06F 17/2705 (2013.01); G06F 17/3069 (2013.01); G06F 17/30598 (2013.01); G06F 17/30654 (2013.01); G06N 7/00 (2013.01);
Abstract

In order to provide a non-factoid question answering system with improved precision, the question answering system () includes: a candidate retrieving unit (), responsive to a question, extracting answer candidates from a corpus storage (); a feature vector generating unit () for generating features from combinations of a question with each of the answer candidates; SVMs () trained to calculate a score of how correct a combination of the question with an answer candidate is, upon receiving the feature vector therefor; and an answer ranker unit () outputting the answer candidate with the highest calculated score as the answer. The features are generated on the basis of the results of morphological analysis and parsing of the question, a phrase in the question evaluated as being positive or negative as well as its polarity, and the semantic classes of nouns in the features.


Find Patent Forward Citations

Loading…