Language Technology

Announcements

3 Nov. 2009 The exam went fairly well. In correcting it, I regularly gave partial credit if a distinction was explained well, even if the names were switched (e.g. in the question on precision vs. recall). A copy of the exam with an answer key is here. The average grade was 6.8 and special congratulations are due to Marko Doornbos and Remko Boschker, who scored the highest on the exam.
An anonymized list of grades is also available .
The grade for language technology is combined with that for speech technology and then reported in Progress.

Description

This site accompanies the "language" half of the course "Taal- en Spraaktechnologie" (Language and Speech Technology"). The part on language technology focuses on the applications of techniques in computational linguistics, where "application" is understood broadly, encompassing both practical and commercial applications, where one attempts to do something practically useful with the technology, but also scientific applications, where one applies technology in order to satisfy scientific curiosity.

Nederlandse Beschrijving (OCASYS)

Goals

The course is designed to give students a broad view of current language technology with some background on how it has developed. Focus points will be the need for corpora and the need for evaluation, with case studies on practical applications in computer-assisted language learning, information extraction and machine translation, and applications to scientific questions in first and second language acquisition and in language variation.

At the end of this course students should be able to evaluate reports on language technology critically, especially in the areas of the case studies.

Readings

See literature schedule.

Book (Background Material)

Ron Cole, Joseph Mariani, Hans Uszkoreit, Giovanni Batista Varile, Annie Zaenen, Antonio Zampolli, and Victor Zue The State of the Art in Human Language Technology Cambridge University Press, 1997. Web Version available here.

Course Coordinator

John Nerbonne, J.Nerbonne@RuG.nl, H1311.436
Office Hours: Mon. 15:30-16:30 (after lecture)

Meeting Times (2009)

Lecture: Mon. 13:15-15:00 pm V 5161.0267

Practical Sessions

There is a separate course "Practicum in Taal- en Spraaktechnologie" in the second half of the fall semester. Students must register separately for that course in the normal way (i.e. not through the instructor of this course).

Exam, Grading

The grade will be based on a written examination, to be held on Mon., Oct. 26, 2009 from 9 am to 12 noon in the Examenhal. There is an opportunity to retake the exam on Thur. Jan 14, 2:00 pm to 5:00, also in the Examenhal.

See the list of example exam questions as an indication of the contents of the exam.

Lectures

Week	Date	Theme	Lecturer	Sheets	Remarks
1.	31 Aug	Why Language Technology?	John Nerbonne	Introduction
		CALL	John Nerbonne	NLP in CALL	GLOSSER
		Language Contact	John Nerbonne	Foreigner Talk
2.	7 Sept.	Habeas Corpus!	John Nerbonne	Corpora
3.	14 Sept.	Discourse	Jennifer Spenader	Discourse
4.	21 Sept.	1st Language Acquisition	Çagri Çötelkin	Simulating Acquisition
			Hartmut Fitz	Syntax Acquisition
5.	28 Sept.	Machine Translation	Gideon Kotzé	Machine Translation	1950's MT
		Information Extraction	John Nerbonne	Extracting Terminologies
6.	5 Oct.	Generation	Daniel de Kok	Fluent Generation
		Variation	Martijn Wieling	Linguistic Varieties
6+	!Thurs.! 8 Oct.	Exam Preparation		Example questions
	12:15-14
	V 5161.0253
9.	Mon. 26 Oct.	Exam	Examenhal
	9 am
+	Thurs. 14 Jan.	Resit Exam	Examenhal
	2 pm

Acknowledgements

Dr. Jennifer Spenader normally teaches this course and kindly made her materials available. About three quarters of the materials on corpora were developed by Jennifer and all of the materials on discourse.

Links

The Association for Computational Linguistics comprises over 2,000 researchers world wide and holds several conferences in different parts of the world every year. The largest are attended by more than 1,000 researchers.

John Nerbonne
Last modified: Mon Aug 17, 2009