32253 English Language and New Technologies

Grades
(Students ids correspond to the last four numbers of the DNI card number)

The general objective of this course is to become acquainted with new technologies applied to natural languages in general and to English in particular.

Activities

The total time assigned to this course is 120 hours (6 cr.) in 15 weeks. This time will be split into the following activities:

Lectures (20 hours)
Internet browsing and information retrieval (30 hours)
Testing of different language technology applications (30 hours)
Writting up of reports (40 hours)

Schedule

	day	time	room	subject
week 1
1. 2.	Tu 10/2 Fr 13/2	12.30-14.00 12.30-14.00	B-16	First contact with the browser, editors and on-line materials. Introduction to Human Language Technologies.
week 2
3. 4.	Tu 17/2 Fr 20/2	12.30-14.00 12.30-14.00	B-16 24-L	Questionnaire 1. Introduction. References See also: HLTCentral (European Programs), DFKI
week 3
5. 6.	Tu 24/2 Fr 27/2	12.30-14.00 12.30-14.00	B-16 24-L	Questionnaire 2. Resources and applications. References See also: Language Technology World, CCL.
week 4
7. 8.	Tu 2/3 Fr 5/3	12.30-14.00 12.30-14.00	B-16 24-L	Questionnaire 3. Speech Technology. References See also: Elsnet, CMU/LTI
week 5
9. 10.	Tu 9/3 Fr 12/3	12.30-14.00 12.30-14.00	B-16 24-L	Questionnaire 4. Information management. References See also: ACL, ISI
week 6
11..	Tu 16/3	12.30-14.00	B-16	Questionnaire 5. Machine Translation. References
week 7
12. 13.	Tu 23/3 Fr 26/3	12.30-14.00 12.30-14.00	B-16 24-L	Questionnaire 5. Machine Translation. References
week 8
14. 15..	Tu 30/3 Fr 2/4	12.30-14.00 12.30-14.00	B-16 24-L	Machine Translation and Machine Aided Translation (topic of report B)
week 9
16.	Tu 6/4	12.30-14.00	B-16	Submission of Report A.
week 10
17. 18.	Tu 20/4 Fr 23/4	12.30-14.00 12.30-14.00	B-16 24-L	List of submitted A reports
week 11
19. 20.	Tu 27/4 Fr 30/4	12.30-14.00 12.30-14.00	B-16 24-L	IInformation Retrieval (topic of report C)
week 12
21. 22..	Tu 4/5 Fr 7/5	12.30-14.00 12.30-14.00	B-16 24-L	Machine Translation and Machine Aided Translation (topic of report B) Information Retrieval (topic of report C)
week 13
23. 24.	Tu 11/5 Fr 14/5	12.30-14.00 12.30-14.00	B-16 24-L	Submission of Report B.
week 14
25. 26..	Tu 18/5 Fr 22/5	12.30-14.00 12.30-14.00	B-16 24-L	List of submitted B reports
week 15
27. 28..	Tu 25/2 Fr 28/5	12.30-14.00 12.30-14.00	B-16 24-L	Submission of Report C. List of submitted C reports
				Grades (Students ids correspond to the last four numbers of the DNI card number)

Objetives

Become acquaintance with new technologies applied to natural languages in general and to English in particular.
Learn the contribution of linguistics to the development of information technologies.
Develop skills using Internet browsers to access and select relevant information.
Use text and hypertext processors for organising retrieved information and for technical reporting.
Review the main techniques and resources developed in computational linguistics.
Focus on practical applications of theoretical and of computational linguistics. We will consider applications such as information extraction, natural language interfaces, multilingual electronic publishing, machine translation, digital document localization, and the multilingual Internet.
Experiment with on-line translation programs and information search enginees.

Methodology

We will learn how to use electronic documentation as referential material for the course. Every week a questionnaire will be set and the students will work on the documentation to answer the questionnaire. This will be combined with practical exercises and the utilization of dedicated software. References and documentation will be provided mainly in the form of hypertext.

Evaluation

In addition to regular attendance and participation, students will submit three reports (see below). A written examination will be set when regular evaluation has not been accomplished. Grading in this course will depend on class attendance and participation (10%), group projects (30%), and an individual report or exam (60%).

Assignments

By April, 6th: Report A, based on notes taken from on-line references (optional and individual)
By May, 14th: Report B. Evaluation of Machie Translation systems (obligatory)
By May, 28th: Report C. Evaluation of search and content retrieval engines (obligatory)

Students that fail to submit reports B or C are not qualified to take the exam.

How to write good reports:

Examples of reports from course 2002/03

Report A

Students will select the topic and title of report A. It can be any thing related to the syllabus, eg. "A review of Human Language Technologies and their role in the Information Society", or "Why is Machine Translation difficult".

It can contain as many text fragments or quotatations (copied and pasted) from the on-line documentation as necessary. Although the author must clarify and justify the relevance of those selected fragments with his own text and the main line of argumentation must be original, not copied!

It is a very important that quotations are acknowledged, i.e. do not forget to provide the source!.

Name of the author, group or institution
Date
Publishers's name, or URL

In addition to the main body of the report, it must also include an

Abstract (no more than 100 words)
Introduction (around 500 words)
Conclusion (around 200 words)

It is very important that these sections contain original text. Try to convey your own personal view and style.

The size of the report will be of 3,000 to 7,000 words (i.e. 15-25 pages).

Have a look to these interesting recomendations:

How to Write a Good Report, by Prof. G. Yadigaroglu, ETHZ (caché)

Student Handbook and Essay Writing Guide, Brock University (caché)

A letter of Professor Michael Stubbs to his students (Englische Sprachwissenschaft Universität Trier ) (caché)

Check also these documents:

Academic paper: Is it worth learning translation technology?

Technical report: Linguistic Diversity on the Internet: Assessment of the Contribution of Machine Translation (caché)

Reports B and C: These will illustrate experiments with on-line resources, and can be developed in groups of four people at most.

References

[DELi's directory of references]

Other on-line

Survey of the State of the Art in Human Language Technology. This "on-line" book, available through Internet, surveys the state of the art of human language technology. The book consists of thirteen chapters written by 97 different authors. Editorial Board: Ronald A. Cole, Editor in Chief; Joseph Mariani; Hans Uszkoreit; Annie Zaenen; Victor Zue. Contents: Spoken Language Input, Written Language Input, Language Analysis and Understanding, Language Generation, Spoken Output Technologies, Discourse and Dialogue, Document Processing, Multilinguality, Multimodality, Transmission and Storage, Mathematical Methods, Language Resources, Evaluation.
Our main reference in corpus linguistics will be Tony McEnery and Andrew Wilson's book on Corpus Linguistics, but there will be other material available (Downloads from Internet).
European Commission, DG XIII. Information Society, (caché)
La Lingüística Computacional, by Juan Carlos Ruiz Antón, Universitat Jaume I.
Multilingual Information Management: Current Levels and Future Abilities, by Eduard Hovy, USC Information Sciences Institute (co-chair) Nancy Ide, Vassar College (co-chair) Robert Frederking, Carnegie Mellon University Joseph Mariani, LIMSI-CNRS Antonio Zampolli, University of Pisa
Information retrieval & natural language processing, by Felisa Verdejo, Julio Gonzalo and Anselmo Peñas at the UNED Natural Language Processing Group under the auspices of the ACO*HUM European network, and partially funded by ELSNET.
Natural Language Research Group (UPC)
Walter J. Ong SJ and the Technology of Writing

In print

Allen, 1987 (1st edition) or 1995 (2nd edition). Natural Language Understanding.
Arnold, Douglas, L. Balkan, Lee Humphreys, and S. Meijr, eds. 1994. Machine translation: introductory guide. Blackwell Publishers.
Gazdar, Gerald & Chris Mellish. 1989. Natural Language Processing In Prolog. An Introduction to Computational Linguistics. Addison-Wesley Publishing Company.
Hutchins, W. J. and Harold Somers. 1992. An introduction to machine translation. Academic Press.
Jones, Daniel. 1996. Analogical Natural Language Processing. 1996. University College London Press.
Jurafsky & Martin. 2000. Speech and Language Processing
McEnery, Tony. 1992. Computational Linguistics: A handbook and toolbox for natural language processing. Sigma Press.
McEnery, Tony and Andrew Wilson. 1996. Corpus Linguistics. Edinburgh University Press .
Manning & Schütze. 1999. Foundations of Statistical Natural Language Processing.
Melby, Alan K. and C.T. Warner. 1995. The Possibility of Language. A discussion of the nature of language, with the implications for human and machine translation. John Benjamins. Amsterdam.