Put AI to work
June 26-27, 2017: Training
June 27-29, 2017: Tutorials & Conference
New York, NY

In-Person Training
Natural language processing with deep learning

Delip Rao (Joostware)
Monday, June 26 & Tuesday, June 27, 9:00am - 5:00pm
Location: Clinton
Secondary topics:  Deep Learning, Natural Language
See pricing & packages
Early Price ends May 12

This course will sell out—sign up today!

Participants should plan to attend both days of this 2-day training course. Training passes do not include access to tutorials on Tuesday.

Delip Rao explores natural language processing using a set of machine-learning techniques known as deep learning. Delip walks you through neural network architectures and NLP tasks and teaches you how to apply these architectures for those tasks.

What you'll learn, and how you can apply it

  • Understand basic concepts in Natural Language Processing (NLP)
  • Understand basic concepts in Deep Learning as it applies to NLP
  • Understand when to use classic NLP solutions versus deep learning-based solutions

Prerequisites:

  • A general understanding of machine learning l(setting up experiments, evaluation, etc.) (useful but not required)
  • A working knowledge of Python
  • Familiarity with TensorFlow

Natural language processing (NLP) involves the application of machine learning and other statistical techniques to derive insights from human language. With large volumes of data exchanged as text (in the form of documents, tweets, email, chat, and so on), NLP techniques are indispensable to modern intelligent applications. The applications range from enterprise to pedestrian.

Delip Rao explores natural language processing using a set of machine-learning techniques known as deep learning. Delip walks you through neural network architectures and NLP tasks and teaches you how to apply these architectures for those tasks.

Day 1:

Traditional approaches to NLP

  • Feature engineering
  • Example: Document classification
  • Machine learning evaluation metrics

Word embeddings

  • What are they?
  • Traditional embedding methods
  • Word2Vec
  • Embedding visualization
  • Application: Word analogy problems
  • Application: Named entity recognition
  • Application: Sentiment analysis

Embedding beyond word units

  • Paragraph2Vec
  • Doc2Vec

Convolutional networks

  • Learning from raw characters
  • Convolutional embeddings of text
  • Application: Chinese document classification


Day 2:

Sequence modeling

  • Why model sequences?
  • RNNs
  • LSTM/GRU
  • Application: Language modeling

Sequence-to-sequence models

Advanced topics

  • Stacked, bidirectional models
  • Attention
  • Recursive/tree-structured models

When to use deep learning and when not to

About your instructor

Delip Rao is the founder of Joostware, a San Francisco-based company specializing in consulting and building IP in natural language processing and deep learning. Delip is a well-cited researcher in natural language processing and machine learning and has worked at Google Research, Twitter, and Amazon (Echo) on various NLP problems. He is interested in building cost-effective, state-of-the-art AI solutions that scale well. Delip has an upcoming book on NLP and deep learning that will be published by O’Reilly Media.

Twitter for deliprao

Conference registration

Get the Platinum pass or the Training pass to add this course to your package. Early Price ends May 12.

Leave a Comment or Question

Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?

Join the conversation here (requires login)