Metric Labeling for Natural Language Processing

Number of patents in Portfolio can not be more than 2000

United States of America Patent

APP PUB NO 20170039183A1
SERIAL NO

15208558

Stats

ATTORNEY / AGENT: (SPONSORED)

Importance

Loading Importance Indicators... loading....

Abstract

See full text

Systems and methods are disclosed for Natural Language Processing (NLP) by applying metric labeling to sentence matching problem by preprocessing a dataset of sentences into objects graphs and label graphs; given an object graph and a label graph, assigning nodes of the object graph to the nodes of the label graph by minimizing an objective function including an assignment cost and a separation cost; and applying the metric labeling to matching two sentences where the objective function value is used as a similarity score between sentences for classification, clustering, or ranking.

Loading the Abstract Image... loading....

First Claim

See full text

Family

Loading Family data... loading....

Patent Owner(s)

Patent OwnerAddress
NEC LABORATORIES AMERICA INC4 INDEPENDENCE WAY SUITE 200 PRINCETON NJ 08540

International Classification(s)

  • [Classification Symbol]
  • [Patents Count]

Inventor(s)

Inventor Name Address # of filed Patents Total Citations
Bai, Bing Princeton Junction, US 65 1026
Osmanlioglu, Yusuf Philadelphia, US 1 4

Cited Art Landscape

Load Citation

Patent Citation Ranking

Forward Cite Landscape

Load Citation