US 11,900,070 B2
Producing explainable rules via deep learning
Prithviraj Sen, San Jose, CA (US); Siddhartha Brahma, San Jose, CA (US); Yunyao Li, San Jose, CA (US); Laura Chiticariu, San Jose, CA (US); Rajasekar Krishnamurthy, Campbell, CA (US); Shivakumar Vaithyanathan, San Jose, CA (US); and Marina Danilevsky Hailpern, San Jose, CA (US)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Feb. 3, 2020, as Appl. No. 16/780,721.
Prior Publication US 2021/0240917 A1, Aug. 5, 2021
Int. Cl. G06F 40/40 (2020.01); G06F 40/284 (2020.01); G06F 40/56 (2020.01); G06F 40/16 (2020.01); G06F 40/289 (2020.01); G06N 20/00 (2019.01); G06N 3/084 (2023.01); G06N 20/10 (2019.01); G06F 18/214 (2023.01)
CPC G06F 40/56 (2020.01) [G06F 18/2155 (2023.01); G06F 40/16 (2020.01); G06F 40/289 (2020.01); G06N 3/084 (2013.01); G06N 20/00 (2019.01); G06N 20/10 (2019.01)] 24 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
receiving, at a deep neural network (DNN), a plurality of sentences each having an associated label;
training the DNN, utilizing the plurality of sentences and associated labels;
producing a linguistic expression (LE) utilizing the trained DNN, wherein the linguistic expression includes a human-readable model, such that the linguistic expression includes a word-based rule that includes one or more human-readable conditions and that is understandable by a human user,
wherein the DNN includes a plurality of intermediate layers, where each of the plurality of intermediate layers corresponds to a condition within the linguistic expression used to perform a determination of a label;
outputting the word-based rule of the human-readable model for output in readable form to the human user;
receiving input from the human user specifying how to adjust at least one of the conditions of the word-based rule;
modifying the at least one condition according to the user input;
receiving an unlabeled sentence;
applying the linguistic expression with the at least one modified condition to the unlabeled sentence for determining a label for the unlabeled sentence; and
in response to determining that one or more conditions of the linguistic expression is not met for the unlabeled sentence, assigning a label to the unlabeled sentence indicating that the condition is not met.