Syntactic Analysis in Language Technology / Syntactic parsing
- Course date: Autumn 2017
- 171212: The groups and times for seminar 2 are now announced. The questions will be announced later.
- 171129: A summary of the mid term evaluation is now available.
- 171127: All assignment instructions are now available both for bachelor and master students.
- 171121: Groups and detailed discussion for the first seminar are now posted.
- 171114: The lecture on Thursday November 23 will be split into around 45 minutes of lecturing and 45 minutes of supervision.
- 171019: The course starts with a first lecture on Tuesday November 7, 13-15 in Turing
These courses give an introduction to methods and algorithms used in automatic syntactic analysis and provides the skills that are required to apply and implement practical systems based on these methods. The courses cover both phrase structure analysis and dependency analysis.
Examination 5LN455 (bachelor)
The course examination is split into four assignments and two seminars. The following grading system will be used both for the complete course and for the assignments: Fail (Underkänd, U), Pass (Godkänd, G), Pass with Distinction (Väl Godkänd, VG). The grade for the course will be G if you get at least G on all assignments and the seminars, VG if you also get the grade VG on at least two of the assignments, of which at least one should be a practical assignment (assignment 2 or 4).
Assignment 1. Hand-in assignment about phrase structure parsing. Detailed description. Deadline: 2017-12-04.
Assignment 2. Implementation of the central component of a phrase structure parser. Detailed description. Deadline: 2017-12-04.
Assignment 3. Hand-in assignment about dependency parsing. Detailed description. Deadline: 2018-01-12.
All assignments should be handed in via Studentportalen.
In addition all students should actively participate in two literature seminars.
Examination 5LN713/5LN717 (master)For 5 credits, the course is examined by means of four assignments:
- Assignment 1: PCFG parsing Implement the CKY parsing algorithm and evaluate the parser using treebank data. Detailed description Deadline: 2017-12-04.
- Assignment 2: Literature review Summarize, analyze and critically review two scientific articles on syntactic parsing in a written report of 3-5 pages. Deadline: 2017-12-18.
- Assignment 3: Dependency parsing Implement a transition-based parsing algorithm and evaluate the parser using treebank data. Detailed description Deadline: 2018-01-12.
- Literature seminar: Actively participate in two literature seminars.
For 7.5 credits, students must in addition do a project chosen together with the teacher. There is no deadline for choosing the project but it is recommended that you do that early in the course. The project should be described in a written report. Deadline: 2018-01-12.
In order to pass the course, a student must pass all assignments (and do the project for extra credits). In order to pass the course with distinction (Väl godkänt), a student must pass at least two assignments (or one assignment and the project) with distinction. The seminars are not graded.
Each assignment has a deadline, which is announced well in advance, see above. Each deadline is at the respective date at 23.59, and all submissions should be done through studentportalen. In case you fail to meet the deadline, you have the chance to re-submit the assignment for a second deadline, which for all assignments is 2018-02-09. In case you fail to meet even the second deadline, the corresponding assignment will be graded as Fail (U). (See Språkteknologiprogrammens Policy för examination (In Swedish) and Examination and continued studies.
Assignments will only be graded in connection with each deadline. If you fail to meet these deadlines, you will have to retake the course the next time it is given. In this case, the course will actually be given again during the first half of the spring term, 2018. After that, it will next be given spring 2019. In case of special circumstances, please contact your teacher BEFORE the deadline it concerns.
More details about the seminars and the preparation for them are posted here. You are divided into the following groups for seminar 1:
- Group A: 13.15-14 (Jenny, Renfun, Matilda, Jonathan, Ebba)
- Group B: 14.15-15 (Ivan, Yang, Ahmed, Oscar, Marcus)
- Group C: 15.15-16 (Paula, Zulipiye, Ingrid, Emelie, Christian)
- Group D: 13.15-14.15 (Jenny, Paula, Zulipiye, Ebba, Emelie, Marcus)
- Group E: 14.30-15.30 (Renfun, Yang, Ingrid, Jonathan, Matilda, Ahmed, Oscar)
There are two literature seminars during the course, which are common for bachelor and master students. In order to get a passing grade on the seminars you need to prepare for them, and be active during the seminar.
The seminars will be held in smaller groups, which will be announced later.
The two seminars are obligatory. If you miss a seminar, or do not participate actively, you will have to do a complementary task. Contact Sara if this is the case.
Daniel Jurafsky and James H. Martin. Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition. Second Edition, Pearson Education, 2009. (Main course book.)
Sandra Kübler, Ryan McDonald, and Joakim Nivre. Dependency Parsing. Morgan and Claypool, 2009. (Electronic edition)
Two research articles on parsing to be discussed during the literature seminars:
- Seminar 1: Mark Johnson. PCFG Models of Linguistic Tree Representations. Computational Linguistics 24(4). Pages 613-632.
- Seminar 2: Joakim Nivre and Jens Nilsson. Pseudo-Projective Dependency Parsing. Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL'05). Pages 99-106. Ann Arbor, USA.
Additional reading is required for the master student courses.
All lectures take place in room Turing (9-2042), unless otherwise noted below
Tuesday 2017-11-07 (13–15) Sara Stymne
Reading: J&M 12.1–12.7.
Thursday 2017-11-09 (13–15) Sara Stymne
The CKY algorithm part 1: Recognition
Reading: J&M 13.1–13.3, 13.4.1.
Tuesday 2017-11-14 (13–15) Sara Stymne
The CKY algorithm part 2: Probabilistic parsing
Reading: J&M 14.1–14.2.
Thursday 2017-11-16 (13–15) Sara Stymne
Treebank grammars and parser evaluation
Reading: J&M 12.4 (again), 14.3, 14.7.
Tuesday 2017-11-21 (13–15) Sara Stymne
The Earley algorithm
Reading: J&M 13.4.2.
Thursday 2017-11-23 (13–15) Sara Stymne
Advanced constituency parsing and supervision
Reading: J&M 14.4-14.6
Deadline for Assignments 1 and 2 (bachelor)
Deadline for Assignment 1 (master)
Tuesday 2017-12-05 (13–15) Sara Stymne
Arc-factored dependency parsing
Reading: KMN 1-2, 4.1, 4.3.
Thursday 2017-12-07 (13–15) Sara Stymne
Collins’ and Eisner’s algorithms
Reading: KMN 4.2 (not 4.2.2).
Tuesday 2017-12-12 (13-15) Sara Stymne
Transition-based dependency parsing
Reading: KMN 2.1.2, 3.1–3.3, 6.1
Thursday 2017-12-14 (13-15) Miryam de Lhoneux
Advanced dependency parsing
Deadline for Assignment 2 (master)
Deadline for Assignments 3 and 4 (bachelor)
Deadline for Assignment 3 and project (master)