1. Dan Jurafsky and James H. Martin, Speech and Language Processing. 3rd Edition, Chapters 10-13.

2. Dan Jurafsky and James H. Martin, Speech and Language Processing. 2nd Edition, Chapters 13.

3. Sandra Kübler, Ryan McDonald, and Joakim Nivre. Dependency Parsing. Morgan and Claypool, 2009. Chapters 1-4 and 6.

1. Two literature discussion/seminar
2. Three assignments
3. One short seminar on selected sections of the books (or other topics)
4. One individual/group project

1. Introduction and course outline
   

2. Syntax
   

3. The CKY algorithm, recognition
   

4. The CKY algorithm, probabilistic parsing
   

5. Treebank Grammars and Parser Evaluation
   

6. The Earley Algorithm
   

7. Dependency Parsing and Dependency Grammar
   

8. Collins’ and Eisner’s Algorithms
   

9. Transition-based Dependency Parsing
   

Seminars are extensions of some sections of the books. The seminars can be presented in groups of at most three students (or individually). Normally, the seminars should not take more 15 minutes. If more time is needed for some cases, it can be discussed. The group members can decide about their way of presentations.

Read the two papers below and prepare yourself for two literature discussions related to each paper. You are expected to actively participate in the discussion. The discussions are based on your seminar group divisions. Each group should prepare a short summary of the paper (1-2 pages). In your summary, try to answer the following questions:

1. What is the most important contribution of the paper?
2. What are the interesting points of the article
3. What parts of the paper are unclear to you

1. Slav Petrov, Leon Barrett, Romain Thibaux, and Dan Klein, 2006, Learning Accurate, Compact, and Interpretable Tree Annotation, Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics - report submission deadline: 2019-05-13. Discussion meeting: 2019-05-15. Here is the plan.

2. Danqi Chen, and Christopher D. Manning, 2014, A Fast and Accurate Dependency Parser using Neural Networks, Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). - report submission deadline: 2019-05-15. Discussion meeting: 2019-05-22. Here is the plan.

1. PCFG parsing: Implement the CKY parsing algorithm and evaluate the parser using treebank data. Detailed description Deadline: 2019-05-13.

2. Summarize, analyze and critically review two scientific articles on syntactic parsing in a written report of 3 pages. Detailed description Deadline 2019-05-30.

3. Dependency parsing: Implement a transition-based parsing algorithm and evaluate the parser using treebank data. Detailed description Deadline 2019-05-22

You need to register yourself to one of the project groups consisting of at most three persons. You can work on your own topic or choose a topic from our parsing project list of topics. You are strongly encouraged to develop your own ideas. The project topics have to be conformed by Ali. You can choose between the two possible project deadlines, the 1st of June, or the 10the of September. By one of these deadlines, you need to upload your project reports to the student portal. The second deadline is mainly intended for you who have failed by the first deadline and need to resubmit your report. However, you can also use the second deadline if you have not submitted the report earlier. The next possibility for resubmission in case of fail is the next time the course is given.