US 12,189,668 B2
Query expansion using a graph of question and answer vocabulary
Seamus R. McAteer, Navan (IE); Ahmed M. M. R. Salem, Dublin (IE); Daniel J. McCloskey, Dublin (IE); and Mikhail Sogrin, Kildalkey (IE)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Apr. 20, 2022, as Appl. No. 17/659,867.
Application 17/659,867 is a continuation of application No. 16/878,596, filed on May 19, 2020, granted, now 11,321,371.
Application 16/878,596 is a continuation of application No. 16/022,898, filed on Jun. 29, 2018, granted, now 10,678,822, issued on Jun. 9, 2020.
Prior Publication US 2022/0245180 A1, Aug. 4, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/33 (2019.01); G06F 16/332 (2019.01); G10L 15/06 (2013.01)
CPC G06F 16/3338 (2019.01) [G06F 16/3329 (2019.01); G06F 16/3334 (2019.01); G10L 15/063 (2013.01)] 25 Claims
OG exemplary drawing
 
1. A computer-implemented method for query expansion using a graph of question and answer vocabulary, the method comprising:
providing a set of training data in a given domain in the form of training question texts and training answer texts;
identifying disjoint answer words in the training answer text that do not occur in the associated training question text;
generating a graph of question word nodes and answer word nodes generated from the set of training data for the given domain in the form of the training question texts and the training answer texts, wherein edges are provided between a disjoint pair of a question word node for a question word in a training question and an answer word node for a disjoint answer word in an associated training answer;
receiving a user query input a search engine;
activating input nodes in the graph for at least some words in the user query input;
applying spreading activation through the graph to propagate a signal which activates nodes, in the graph for at least some words in the user query input, to generate candidate words for expansion of the user query input; and
providing the candidate words to the search engine for expansion of the user query input.