Daniel T Campos

US Patent:

20210326742, Oct 21, 2021

Filed:

Apr 16, 2020

Appl. No.:

16/850886

Inventors:

- Redmond WA, US
Chenyan XIONG - Bellevue WA, US
Paul Nathan BENNETT - Redmond WA, US
Saurabh Kumar TIWARY - Bellevue WA, US
Daniel Fernando CAMPOS - Seattle WA, US
Xia SONG - Redmond WA, US
Nicholas Eric CRASWELL - Seattle WA, US

International Classification:

G06N 20/00
G06N 5/04
G06K 9/62
G06F 17/16

Abstract:

A computer-implemented technique is described herein for assisting a user in advancing a task objective. The technique uses a suggestion-generating system (SGS) to provide one or more suggestions to a user in response to at least a last-submitted query provided by the user. The SGS may correspond to a classification-type or generative-type neural network. The SGS uses a machine-trained model that is trained using a multi-task training framework based on plural groups of training examples, which, in turn, are produced using different respective example-generating methods. One such example-generating method constructs a training example from queries in a search session. It operates by identifying the task-related intent the queries, and then identifying at least one sequence of queries in the search session that exhibits a coherent task-related intent. A training example is constructed based on queries in such a sequence.

US Patent:

20210004439, Jan 7, 2021

Filed:

Jul 2, 2019

Appl. No.:

16/460853

Inventors:

- Redmond WA, US
Chuan HU - Redmond WA, US
Arnold OVERWIJK - Redmond WA, US
Junaid AHMED - Bellevue WA, US
Daniel Fernando CAMPOS - Seattle WA, US
Chenyan XIONG - Bellevue WA, US

Assignee:

Microsoft Technology Licensing, LLC - Redmond WA

International Classification:

G06F 17/27
G06K 9/62
G06N 3/08

Abstract:

A system for extracting a key phrase from a document includes a neural key phrase extraction model (“BLING-KPE”) having a first layer to extract a word sequence from the document, a second layer to represent each word in the word sequence by ELMo embedding, position embedding, and visual features, and a third layer to concatenate the ELMo embedding, the position embedding, and the visual features to produce hybrid word embeddings. A convolutional transformer models the hybrid word embeddings to n-gram embeddings, and a feedforward layer converts the n-gram embeddings into a probability distribution over a set of n-grams and calculates a key phrase score of each n-gram. The neural key phrase extraction model is trained on annotated data based on a labeled loss function to compute cross entropy loss of the key phrase score of each n-gram as compared with a label from the annotated dataset.

Address:

8926 Rdg Holw St, San Antonio, TX 78250

VIN:

1B3HB48B37D513662

Make:

DODGE

Model:

CALIBER

Year:

2007