Weekly overview

Monday Tuesday
 

L1: Introduction & Looking at data

Tue 22 Aug., 10.15, Perl

Recommended reading

For the descriptive statistics part, any of the following will cover the lecture
  • Cartoon Guide: Ch. (1-) 2, "Data Description"
  • Nutshell: Ch. 4, "Descriptive Statistics and Graphical Displays", p. 83-120
  • OpenIntro 1.1, 1.2.0- 1.2.2, 1.6.0-1.6.5, 1.7.0-1.7.2
  • Moore and McCabe: Ch. 1, "Looking at Data - Distributions", sec. 1.1-1.2

Lab1, Python, NLTK, NumPy, Graphics

Mon 28 Aug, 12.15 Fortress
  • Exercises (complete)
    • (corrected typos, added part on plotting, 24-AUG)
    • (corrected one more typo "np.oness", 25-AUG-0945)

Tut1, Probabilities

28 Aug., 14.15, Perl
Any of the following will cover the lecture
  • Cartoon Guide: Ch. 3, "Probability"
    + Ch. 4 "Random variables"
  • Nutshell: Ch. 2, "Probability"
  • OpenIntro Ch. 2, "Probability", sec. 2.1-2.4
  • Moore and McCabe: Ch. 4, "Probability"

L2: Classification

Tue 29 Aug., 10.15, Perl

Mandatory reading

Lab2, Texts

Mon 4 Sep, 12.15 Fortress

Tut2, Probability distributions

Mon 4 Sep., 14.15, Perl
Any of the following will cover the lecture
  • Cartoon Guide: Ch. 5 + CH. 6
  • Nutshell: Ch. 3, "Inferential statistics"
  • OpenIntro Ch. 3, "Distributions",
    • in particular, Sec. 3.3.1, Sec. 3.4, Sec. 3.1
  • Moore and McCabe:

L3: Classification contd.

Tue 5 Sept., 10.15, Perl

Lab3

Mon 11 Sep, 12.15 Fortress

L4: Evaluation and statistics

NB, moved to: Mon 11 Sept., 14.15, Perl

This will not follow any text book. The main points are covered in textbooks on statistics (but it is somewhat hidden, as they also cover a lot more.)

Any of the following will cover the lecture
  • Cartoon Guide: Ch. 5 +8+9
  • Nutshell: Ch. 3, "Inferential statistics"
  • OpenIntro Ch. 3, "Inferences for categorical data",
    • in particular, Sec. 6.5 and some of Sec. 6.1 and 6.2
  • Moore and McCabe: Ch.  8, Ch. 5

Lab4

Mon 18 Sep, 12.15 Fortress

L5: Evaluation and statistics, contd.

Lab5

Mon 25 Sep, 12.15 Fortress

L6: Dependency grammar and data-driven dependency parsing

Tue 26 Sep., 10.15, Perl

Presentation

Mandatory reading

  1. Jurafsky and Martin, Speech and Language Processing, 3ed, Ch.14 "Dependency parsing"
  2. Nivre et al. (2006). Maltparser: A data-driven parser-generator for dependency parsing. In Proceedings of LREC-2006.

Recommended reading

  1. NLTK Book, Ch. 8, "Analyzing sentence structure"
  2. Zwicky, A. M. (1985). Heads. Journal of linguistics, 21(1), 1-29.
  3. Nivre et al. (2016). Universal Dependencies v1: A Multilingual Treebank Collection. In Proceedings of LREC-2016.

Lab6

Mon 2 Oct, 12.15 Fortress
  • Finishing Data-driven Dependency Parsing lecture
  • Working with MaltParser

Slides

Slides, print version

L7: Modern approaches to dependency parsing

Tue 3 Oct., 10.15, Perl

Presentation

Mandatory reading

  1. Jurafsky D. & Martin J., Speech and Language Processing, 3ed, Ch.14 "Dependency parsing"
  2. McDonald, R., & Nivre, J. (2007). Characterizing the errors of data-driven dependency parsing models. In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL).
  3. Straka, M., & Straková, J. (2017). Tokenizing, POS Tagging, Lemmatizing and Parsing UD 2.0 with UDPipe. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies.

Recommended reading

  1. Chen, D., & Manning, C. (2014). A fast and accurate dependency parser using neural networks. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP) (pp. 740-750).
  2. Zeman, D. et al. (2017). CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, 1-19.
  3. Alberti, C. et al. (2017). SyntaxNet Models for the CoNLL 2017 Shared Task. arXiv preprint arXiv:1703.04929.
  4. Dozat, T., Qi, P., & Manning, C. D. (2017). Stanford's Graph-based Neural Dependency Parser at the CoNLL 2017 Shared Task. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies.
  5. Qi, P., & Manning, C. D. (2017). Arc-swift: A Novel Transition System for Dependency Parsing. In Proceedings of ACL-2017.

No lab 9 Oct.

L8: Tokenization, tagging, information extraction

Tue 10 Oct., 10.15, Perl

Mandatory reading

  • Jurafsky and Martin, Speech and Language Processing, 3ed,
    • Ch. 2, "Regular expressions, ...", sec 2.1-2.3 (except 2.3.3 and details of 2.3.1)
      (sec. 2.1 is the same in the 2. ed)
    • Ch. 10, "Part-of_Speech Tagging", sec 10.1-10.3 (this is roughly the same as 2.ed 5.1-5.3.
      The second edition also includes a useful table over the Brown tagset.)
    • Ch. 21, Information Extraction, xxx
  • NLTK Book, Ch. 7"Extracting information from text", Sec. 5.1-5.3

Lab7

Mon 16 Oct, 12.15 Fortress

L9: Information extraction, contd.

Tue 17 Oct., 10.15, Perl

No lab 23 Oct.

L10:Logistic regression

Tue 24 Oct., 10.15, Perl

Mandatory reading

Recommended reading

Lab8

Mon 30 Oct, 12.15 Fortress

L11: Word sense disambiguation today

Tue 31 Oct., 10.15, Perl

Presentation

Mandatory reading

  1. Jurafsky D. & Martin J., Speech and Language Processing, 3ed, Ch. 17 "Computing with word senses"
  2. Navigli, R. (2012). A quick tour of word sense disambiguation, induction and related approaches. SOFSEM 2012: Theory and practice of computer science.

Recommended reading

  1. Kilgarriff, A. (1997). I don’t believe in word senses. Computers and the Humanities, 31(2).
  2. Moro, A., & Navigli, R. (2015). SemEval-2015 Task 13: Multilingual All-Words Sense Disambiguation and Entity Linking. In SemEval@ NAACL-HLT.
  3. Papandrea, S., et al. (2017). SUPWSD: A Flexible Toolkit for Supervised Word Sense Disambiguation. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing: System Demonstrations.
  4. Panchenko, A., et al.  (2017). Unsupervised, Knowledge-Free, and Interpretable Word Sense Disambiguation. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing: System Demonstrations.

Lab9

Mon 6 Nov, 12.15 Fortress

Exercises with Word Sense Disambiguation

  • Lesk algorithm
  • Supervised WSD
  • Word Sense Induction

Slides

Git repository

L12: Introduction to semantic role labeling

(with the discussion of Project A)

Tue 7 Nov., 10.15, Perl

Presentation

Mandatory reading

  1. Jurafsky D. & Martin J., Speech and Language Processing, 3ed, Ch. 22 "Semantic Role Labeling"
  2. Lluís Màrquez, et al. (2008). Semantic Role Labeling: An Introduction to the Special Issue. Computational linguistics, 34(2), 145-159.

Recommended reading

  1. Fillmore, C. J. (2012). Encounters with language. Computational Linguistics, 38(4), 701-718.
  2. Palmer, M., et al. (2005). The proposition bank: An annotated corpus of semantic roles. Computational linguistics, 31(1), 71-106.

Lab10

Mon 13 Nov, 12.15 Fortress
  1. Exercises with Word Sense Disambiguation (continued)
    Slides
  2. Exercises with Semantic Role Labeling
    Slides

Git repository

L13: Modern approaches to semantic role labeling

Tue 14 Nov., 10.15, Perl

Presentation

Mandatory reading

  1. Jurafsky D. & Martin J., Speech and Language Processing, 3ed, Ch. 22 "Semantic Role Labeling"
  2. Haji?, J. et al (2009). The CoNLL-2009 shared task: Syntactic and semantic dependencies in multiple languages. Proceedings of the 13th Conference on Computational Natural Language Learning: Shared Task. Association for Computational Linguistics.

Recommended reading

  1. Vasin Punyakanok et al (2008). The Importance of Syntactic Parsing and Inference in Semantic Role Labeling. Computational linguistics, 34(2), 257-287.
  2. Roth, M., & Lapata, M. (2016). Neural semantic role labeling with dependency path embeddings. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics.
  3. Marcheggiani, D. at al (2017). A simple and accurate syntax-agnostic neural model for dependency-based semantic role labeling. Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017). Association for Computational Linguistics.

Lab11

Mon 20 Nov, 12.15 Fortress

Working on Project B.

Code

The regular lectures are finished

Repetition and exercises

Mon 11 Dec., 1215

Slides on Project B results

(Possible: repetition and exercises)

Tue12 Dec., 1015

 

Published Aug. 21, 2017 4:48 PM - Last modified Dec. 11, 2017 2:55 PM