Dependency Grammar and Tagging with SpaCy / Kramer, Aaron.

Format:

Video

Author/Creator:

Kramer, Aaron, author.

Language:

English

Subjects (All):

Natural language processing (Computer science).

Python (Computer program language).

Genre:

Electronic videos.

Physical Description:

1 online resource (1 video file, approximately 24 min.)

Edition:

1st edition

Place of Publication:

Infinite Skills, 2017.

System Details:

video file

Summary:

Dependency grammar is a powerful way to represent syntactic relationships within a sentence. More sophisticated than bag-of-words representations, it's used in natural language processing tasks like feature engineering, opinion mining, information retrieval, and relation extraction. In this course, which is designed for basic to intermediate level Python programmers, you'll learn how to represent dependency grammar as an extension to valency grammar and use it with spaCy. Discover valency grammar and how it's used to express word relationships Understand dependency grammar as a typed extension to valency grammar Explore the expressivity, assumptions, and limitations of dependency grammar Learn how to traverse parses with spaCy for various applications Gain experience training a spaCy parser on a Twitter dataset Aaron Kramer is a data scientist and engineer with Los Angeles based DataScience Inc. He is a spaCY contributor who holds a BA in Economics from Swarthmore College and is the author of multiple O'Reilly titles on the subject of natural language processing.

Participant:

Presenter, Aaron Kramer.

Notes:

Online resource; Title from title screen (viewed March 27, 2017)

Title from title screen (viewed April 14, 2017).

Date of publication from resource description page.

OCLC:

982385671