Basic Information
We Will Cover Timely Problems Such As Multilingual Learning and Joint Processing of Language and Image. We Will Discuss Nlp For The Web Where These Problems Are Prominent. Particularly, We Will Discuss And Compare Methods Based On Bayesian Inference (e.g. Topic Models), Convex Linear Structured Prediction (e.g. Conditional Random Fields (crfs)) and Deep Neural Networks (dnns) For Multi Task And Multi-language Learning Problems. Our Focus Will Be On Problems at The Main Focus of The Resarch Community With A Particular Focus On Language Processing in The Web, Where Language Is Processed Jointly With Other Modalities Such As Author Properties, Imgaes and Feedback From Other Users. a Particular Ateention Will Be Given to Covering Advanced Computational Methods in Deep Learning And Advanced Approximation Methods in Graphical Models. Learning Outcomes# In The End of The Course# 1. The Student Will Be Familiar With Advanced Topics in Natural Language Processing, With a Focus On Multilingual and Cross-lingual Learning, Joint Processing of Language and Image and Language Processing On The Web. 2. The Student Will Be Familiar With Advanced Papers in The Field. 3. The Student Will Implement a Project Based On The Course Material, Using Real World Data.
Faculty: Data and Decision Sciences
|Undergraduate Studies
|Graduate Studies
Pre-required courses
46195 - Machine Learning or 46202 - Data Analysis or 46203 - Planning and Reinforcemet Learning or 96411 - Machine Learning 1 or 236756 - Introduction to Machine Learning
Course with no extra credit
97215 - Methods in Natural Language Processing 236299 - Intr. to Natural Language Processing