Semantic Computing

Aus International Center for Computational Logic
Wechseln zu:Navigation, Suche

Semantic Computing

Lehrveranstaltung mit SWS 2/2/0 (Vorlesung/Übung/Praktikum) in WS 2018

Dozent

Tutor

Umfang (SWS)

  • 2/2/0

Module

Leistungskontrolle

  • Mündliche Prüfung

Semantic computing tackles the computational understanding of meanings of contents and their machine readable representation. It refers to a set of methods for machines to acquire common-sense and linguistic knowledge. This introductory course covers a broad overview of fundamental theories and methodologies in semantic computing, such as an introduction to linguistics and Natural Language Processing (NLP), and a basic practical skill set of machine learning methods for natural language understanding, such as word embeddings, knowledge graph embeddings, Support Vector Machines (SVM), and neural networks. For neural networks the focus of this semester will be on the recurrent type (RNNs) and in terms of machine learning paradigms we will discuss selected algorithms of supervised, unsupervised, and reinforcement learning. At the very end, the course will look at how to employ the discussed methods to learn structured knowledge, such as ontologies, from natural language text.

Schedule

The lecture will take place each Monday as follows with the first lecture on 19 October 2018 and the last on 01 February 2019.

  • Friday, 9.20 -- 10.50 am (lecture), Room APB/E005
  • Friday, 11.10 -- 12.40 am (tutorial), Room APB/E005 or PC-Pool APB-E065
  • Monday, 14.1.2019, 11.10 --12.40 am (lecture), Room APB/E007
  • Monday, 14.1.2019, 1.00 -- 2.30 pm (tutorial, Room APB/E0069

Lecture free periods are:

  • Friday, 12 October 2018
  • Friday, 14 December 2018 (instead: Monday 14.1.2019 11.10 -- 2.30 pm; see above)
  • Saturday, 22 December 2018 to Sunday 06 January 2019

Materials

Lecture

All slides of lectures for implementations will be provided here shortly before each lecture (in "Dates and Materials" on this page).

Tutorial

All materials for the tutorials can be found at this linked Semantic Computing GitHub.

Platforms

This lecture uses the e-learning platform OPAL to support learning, discussing and exchanging contents related to the topic and lecture of Semantic Computing. Please go to THIS LINK, login with your ZIH login and join the Semantic Computing online platform. Feel free to add contents to the Wiki which is currently an infant and with your help will grow over the course of the semester. In other words, if you read or see contents potentially interesting to others, feel free to summarizes it in your words in SemComp Wiki.

Contact

Questions are encouraged during the lecture. If you wish to discuss any questions or issues offline, feel free to post into the Semantic Computing forum on the OPAL platform or e-mail me. There will be no official office hour. For personal appointments (office APB 2034), please also send me an e-mail.

Lecture slides and tutorials provide a broad overview on the wide range of topics covered in this lecture. For those interested in further readings to achieve a deeper understanding of individual topics the following literature listing might be useful. Please be aware that this list is not complete and I might update it based on topics coming up in class throughout the semester.

Resources

Machine Learning

  • Mitchell, T. M. (1997). Machine Learning, McGraw-Hill Higher Education. New York.
  • Bishop, C. (2006). Pattern Recognition and Machine Learning. Springer.
  • Murphy, K. P. (2012). Machine Learning: a Probabilistic Perspective. MIT Press, Cambridge, MA, USA.
  • Grus, J. (2015). Data Science from Scratch. O'Reilly Media.
  • Chapelle, O., Schölkopf, B. and Zien, A. (2006). Semi-supervised learning. MIT Press. online edition
  • Witten, I. H., Frank, E., Hall, M. A. and Pal, C. J. (2016). Data Mining: Practical machine learning tools and techniques. Morgan Kaufmann.
  • Goodfellow, I., Bengio, Y. and Courville, A. (2016). Deep Learning, online edition

Linguistics

  • Lappin, S. (2008). An Introduction to Formal Semantics. In: The Handbook of Linguistics, Wiley, pp. 369-393, online edition
  • Yule, G. (2014). The Study of Language. Cambridge. 5th ed. Cambridge University Press.
  • Cruse, A. (2011). Meaning in Language: An Introduction to Semantics and Pragmatics. Oxford University Press.
  • O'Grady, W., Archibald, J. and Katamba , F. (2009). Contemporary Linguistics: An Introduction. 6th ed. Bedford / St. Martin's, 2009.
  • Crystal, D. (1997). The Cambridge Encyclopedia of Language. Cambridge University Press.

Computational Linguistics

  • Jurafsky, D. and Martin, J.H. (2009). Speech and Language Processing: An Introduction to Natural Language Processing, Speech Recognition, and Computational Linguistics. 2nd edition. Prentice-Hall, online 2nd edition, partial 3rd edition
  • Bird, S., Klein, E. and Loper, E. (2009). Natural Language Processing with Python. O'Reilly Media, online edition
  • Manning, C.D. and Schütze, H. (1999). Foundations of Statistical Natural Language Processing. The MIT Press: Cambridge, Massachusetts.
  • Manning, C.D., Raghavan, P. and Schütze, H. (2008) Introduction to Information Retrieval. Cambridge University Press. online edition

Finding Conference Contributions

Veranstaltungskalender abonnieren (icalendar)

Vorlesung Lecture 1 DS2, 19. Oktober 2018 in APB E005 Download
Vorlesung Lecture 2 DS1, 26. Oktober 2018 in APB E005 Download
Vorlesung Lecture 3 DS1, 2. November 2018 in APB E005 Download
Vorlesung Lecture 4 DS1, 9. November 2018 in APB E005 Download
Vorlesung Lecture 5 DS1, 16. November 2018 in APB E005 Download
Vorlesung Lecture 6 DS1, 23. November 2018 in APB E005 Download
Vorlesung Lecture 7 DS1, 30. November 2018 in APB E005 Download
Vorlesung Lecture 8 DS1, 6. Dezember 2018 in APB E005 Download


Kalender

Lade …