Kensho Technologies, LLC

Aron Szanto

Domenic Puzio

Sireesh Gururaja

Michael Ramsey

Benjamin Hsu

Anthony Liu

Gabriel Parlato-Altay

A method for dynamically updating a machine learning model is provided. The method comprises receiving first data comprising a first number of documents, training a first machine learning model with the first data, and releasing the first machine learning model for use. After receipt of the first data, second data is received comprising a second number of documents. A concept labeling engine, according to the first machine learning model, labels a concept for at least one document in the second data. Responsive to determining that a distribution of words in the second data deviates from a distribution of words in the first data beyond a specified threshold, the first machine learning model is retrained with at least part of the second data, the retraining producing a second machine learning model; and releasing the second machine learning model for use.

Dynamically updated text classifier

Methods and systems for dynamically updating machine learning models such as text classifiers. One of the methods includes: receiving first data; producing a first machine learning model using the first data; releasing the first machine learning model for use; receiving second data after receipt of the first data; determining that the second data has a difference metric relative to the first data that exceeds a difference threshold; retraining the first machine learning model using at least part of the second data, the retraining producing a second machine learning model; and releasing the second machine learning model for use.

Methods, and systems for named entity recognition and disambiguation. One of the methods includes: receiving a document; extracting a plurality of mentions within the document; clustering the plurality of mentions to produce at least one cluster; identifying a plurality of candidate entities for the cluster; pairing each candidate entity and the cluster to create a plurality of candidate entity-cluster pairings; generating features for each candidate entity-cluster pairing; and selecting an entity, from the plurality of candidate entities, for the cluster based at least in part on features of a candidate entity pairing.

Growing community of inventors

New York, NY, United States of America

Aron Szanto