NLP from scratch : solving the cold start problem for natural language processing / Michael Johnson, Norris Heintzelman.

Format:

Video

Author/Creator:

Johnson, Michael L., on-screen presenter.

Contributor:

Heintzelman, Norris, on-screen presenter.

O'Reilly & Associates, publisher.

Language:

English

Subjects (All):

Natural language processing (Computer science).

Machine learning.

Business logistics--Data processing.

Business logistics.

Big data.

Strata Conference (2019 : San Francisco, California).

Strata Conference.

Physical Description:

1 online resource (1 streaming video file (43 min., 17 sec.)) : digital, sound, color

Other Title:

Natural language processing from scratch

Place of Publication:

[Place of publication not identified] : O'Reilly Media, 2019.

Summary:

"Michael Johnson and Norris Heintzelman (Lockheed Martin) share several techniques they've implemented to build classification and NER models from scratch. They lead a tour through this space as it applies to NLP and demonstrate their approach and architecture for the following techniques: Weak supervision for news documents: Using rules base classification alongside deep learning system for text classification; Active learning and human in the loop: Explaining how breakthroughs in transfer learning for NLP have impacted their active learning framework for building an LSTM-based relevance model; Creative training sets: Identifying and cleaning already-labeled datasets, training classifier on "only" positive examples; NER adjudication: Combining knowledge from several annotation sources that leverages the strengths of each source. For each of these topics, Michael and Norris outline the theoretical foundation, the implementation architecture, and tools used and discuss the problems they encountered, so you can avoid making the same mistakes."--Resource description page.

Participant:

Presenters, Michael Johnson, Norris Heintzelman.

Notes:

Title from title screen (viewed January 10, 2020).

OCLC:

1135503659