Jun M Araki

US Patent:

20220328038, Oct 13, 2022

Filed:

Apr 9, 2021

Appl. No.:

17/226594

Inventors:

- Stuttgart, DE
Jun Araki - San Jose CA, US
Hyeongsik Kim - San Jose CA, US

International Classification:

G10L 15/18

Abstract:

A computer-implemented system and method relate to natural language processing and knowledge representation and reasoning. A first dataset is created that includes input data and situational data. The situational data provides context for the input data. An encoder is configured to generate an encoded representation of the first dataset. The encoder includes at least an encoding network of a first pre-trained generative machine learning model, which relates to a generative knowledge graph. A decoder includes a decoding network of a second pre-trained generative machine learning model. The decoder is configured to generate response data based on the first dataset by decoding the encoded representation. The decoder is also configured to generate event-centric knowledge based on the first dataset by decoding the encoded representation. The input data and the response data are connected to the same event-centric knowledge via the generative knowledge graph. For example, the event-centric knowledge includes goal data, which is inferred from the input data and the situational data.

US Patent:

20220269863, Aug 25, 2022

Filed:

Feb 22, 2021

Appl. No.:

17/181288

Inventors:

- Stuttgart, DE
Jun Araki - San Jose CA, US

International Classification:

G06F 40/30
G06F 40/284
G06F 40/166
G06N 3/08
G06N 3/04

Abstract:

A system and method are disclosed that enable rapid and cost-effective human-in-the-loop synthesis of domain-specific textual training data for a deep learning model. The data augmentation process incorporates a sentence generator, a sentence classifier, and weak-supervision by a domain expert that is ‘in the loop.’ Generally, both the sentence generator and the sentence classifier are implemented as machine learning models. The sentence generator generates new sentences based on manually labeled sentences and the sentence classifier generates labels for the newly generated sentences. The new sentences are corrected or verified by a domain expert and then used to retrain one or both of the sentence generator and the sentence classifier.