CSE 5525: Speech and Language Processing

Fundamentals of natural language processing, automatic speech recognition; lab projects concentrating on building systems to process written and/or spoken language.

Details
Topics:
Textbooks:
There are two excellent NLP textbooks that are freely available online. I will assign readings from both - there is a lot of value in seeing multiple perspectives on the same material. If a concept you encounter seems confusing at first, try reading about it in the other textbook to get a different perspective.
Grading

Grading will be based on:

Participation and in-class Exercises (10%)

You will receive credit for asking and answering questions related to the homework on Piazza, engaging in class discussion and participating in the in-class exercises.

Homeworks (50%)

The homeworks will include both written and programming assignments. Homework should be submitted to the Dropbox folder in Carmen by 11:59pm on the day it is due (unless otherwise instructed). Each student will have 3 flexible days to turn in late homework throughout the semester. As an example, you could turn in the first homework 2 days late and the second homework 1 day late without any penalty. After that you will loose 20% for each day the homework is late. Please email your homework to the instructor in case there are any technical issues with submission.

Midterm (20%)

There will be an in-class midterm on March 8.

Final Projects (20%)

The final project is an open-ended assignment, with the goal of gaining experience applying the techniques presented in class to real-world datasets. Students should work in groups of 3-4. It is a good idea to discuss your planned project with the instructor to get feedback. The final project report should be 4 pages. The report should describe the problem you are solving, what data is being used, the proposed technique you are applying in addition to what baseline is used to compare against.

Resources
  • Piazza (discussion, announcements, etc...). http://piazza.com/osu/spring2019/5525
  • Carmen (homework submission + grades). https://osu.instructure.com/courses/55482
  • Academic Integrity
    Any assignment or exam that you hand in must be your own work (with the exception of group projects). However, talking with others to better understand the material is strongly encouraged. Copying a solution or letting someone copy your solution is considered cheating. Everything you hand in must be your own words. Code you hand in must be written by you, with the exception of any code provided as part of the assignment. Any collaboration during an exam is considered cheating. Any student who is caught cheating will be reported to the Committee on Academic Misconduct. Please don't take a chance - if you are having trouble understanding the material, let us know and we will be happy to help.
    Homework
  • Homework 1 (Due 1/23, submit report and code to Dropbox on Carmen)
  • Homework 2 (Due 2/9, submit report, code and written solution to Dropbox on Carmen)
  • Homework 3 (Due 3/4), submit report and code to Dropbox on Carmen)
  • Anonymous Feedback
    Tentative Schedule:
    Schedule
    Date Topic Required Reading Suggested Reading
    1/9 Course Overview J+M, 3rd Edition Chapter 1
    1/11 Machine Learning (classification) Eisenstein 2.0-2.5, 4.1,4.3-4.5, CIML, 4.1-4.4, 4.6-4.7
    1/16 Machine Learning (cont.) Eisenstein 2.0-2.5, 4.1,4.3-4.5, CIML, 4.1-4.4, 4.6-4.7 CIML Chapter 5 (Linear Models / SVM)
    1/18 Multiclass Learning J+M Chapter 5
    1/23 Multiclass Learning (cont)
    1/25 Sequence Tagging Eisenstein 7.0-7.4,
    1/30 Viterbi Algorithm J+M Chapter 8,
    2/6 Viterbi (cont.) and Conditional Random Fields Eisenstein 7.5, 8.3, Manning 2011 “Part-of-Speech Tagging from 97% to 100%: Is It Time for Some Linguistics?”
    2/12 NER, Neural Networks in NLP Eisenstein 3.1-3.3, J+M 7.1-7.4 Goldberg 1-4
    2/19 Word Embeddings Eisenstein 3.3.4, 14.5, 14.6, J+M 6 Goldberg 5, word2vec, Levy, GloVe, Dropout
    2/27 Recurrent Neural Networks J+M Chapter 9, Goldberg 10,11,
    3/1 Recurrent Neural Networks (cont) + Convolutional Neural Networks, Neural CRFs Eisenstein 3.4, 7.6 Goldberg 9, Kim, Collobert and Weston, Neural NER
    3/12 Machine Translation Eisenstein 18.1, 18.2
    3/20 Encoder-Decoder Networks Seq2Seq
    3/22 Encoder-Decoder Networks (cont) and Information Extraction Eisenstein 13, 17