Course: COMPSCI 690D, Spring 2019
Instructors: Mohit Iyyer and Brendan O'Connor
Location: See SPIRE (currently Hasbrouck Lab Addition room 124)
Time: TuTh 11:30AM - 12:45PM
Contact: cs690dinstructors at gmail
Link to Piazza, where all course information will be posted.
This course offers an introduction to the models and principles behind state-of-the art deep learning techniques applied to natural language processing problems. It is intended for graduate students in computer science and linguistics who are (1) interested in learning about cutting-edge research progress in NLP and (2) familiar with machine learning fundamentals. We will cover a variety of models, including vector-based word representations, basic neural network architectures (e.g., convolutional, recurrent), and more advanced variants of these networks that are especially useful for NLP (e.g., attention-based or memory-augmented). We will also see these models in action on a variety of NLP tasks, including text classification, question answering, and text generation.
I'd like something to read early!: Some people have asked for readings before the semester starts.
Check out Jacob Eisenstein's draft textbook, Natural Language Processing.
During the course, we may use some readings from it and other sources.
Goodfellow et al., 2016, Deep Learning,
and Jurafsky and Martin draft 3rd ed., Speech and Language Processing.
Enrollment questions: The course is already full, so we are not sure
if we will be able to accomodate everyone who wishes to enroll. If you'd like
to take this course but cannot register, please let us know your interest.
- Send us information through either:
- Submit an override request through the online system.
- OR, if that doesn't work, email firstname.lastname@example.org.
- In any case, be sure to describe each of the following.
- What type of student you are: what institution you are from (UMass or other),
what department you are in (CS, Linguistics, etc.),
what degree program (Bachelors, Masters, PhD, etc.),
and what year in the program.
- What is your background in (1) natural language processing, (2) machine learning, and (3) linguistics.
- Why you are interested in the course.
- Any special considerations, such as if you are graduating soon.
The University of Massachusetts Amherst is committed to providing an equal educational opportunity for all students. If you have a documented physical, psychological, or learning disability on file with Disability Services (DS), you may be eligible for reasonable academic accommodations to help you succeed in this course. If you have a documented disability that requires an accommodation, please notify me within the first two weeks of the semester so that we may make appropriate arrangements.
Since the integrity of the academic enterprise of any institution of higher education requires honesty in scholarship and research, academic honesty is required of all students at the University of Massachusetts Amherst. Academic dishonesty is prohibited in all programs of the University. Academic dishonesty includes but is not limited to: cheating, fabrication, plagiarism, and facilitating dishonesty. Appropriate sanctions may be imposed on any student who has committed an act of academic dishonesty. Instructors should take reasonable steps to address academic misconduct. Any person who has reason to believe that a student has committed academic dishonesty should bring such information to the attention of the appropriate course instructor as soon as possible. Instances of academic dishonesty not related to a specific course should be brought to the attention of the appropriate department Chair. Since students are expected to be familiar with this policy and the commonly accepted standards of academic integrity, ignorance of such standards is not normally sufficient evidence of lack of intent. See the Honesty Policy.