32253 English Language and New Technologies

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

Questionnaire 1

Describe the different senses and usages of the terms
- Human Language Technologies
- Natural Language Processing
- Computational Linguistics
- Language Engineering
Does the notion of "Information Society" have any relation to Human Language?
Is there any concern in Europe with Human Langugae Technologies?
What is the current situation of the HLTCentral.org office?

On-line references

Language Engineering and the Information Society (Document from I*M Europe)
Living and Working Together in the Information Society (Discussion Document from HLTCentral).
Information Policy for an Information Society (Paper by Mairéad Browne - caché).
Human Language Technologies and the information society (Presentation of Action Line, by the EC: caché)
What is Language Technology, by Hans Uszkoreit (caché in PDF)
What is Computational Linguistics?, by Hans Uszkoreit (caché)

Questionnaire 2

Which are the main techniques used in Language Engineering?
Which language resources are essential components of Language Engineering?
Check for the following terms (choose at least five):
- language guesser
- lemmatizer
- tokenization
- multimodal corpora
- part-of-speech tagging
- stemmer
- morphological analysis
- shallow parser
- spoken language translation
- translator's workbench
- shallow parser
- formalism
- speech recognition
- text alignment
- authoring tools
- controlled language
- domain

On-line references

http://en.wikipedia.org/wiki/Natural_language_processing
Language Technology World
Language Engineering (Brouchure by HLTCentral: caché)

Questionnaire 3

What is the state of the art in Speech Technology?
Explain the main differences between speech recognition and speech synthesis.
Speech-to-speech machine translation. List and describe at least three projects.

On-line references

Ron Cole and Victor Zue. 1996. Spoken Language Input, http://cslu.cse.ogi.edu/HLTsurvey/ch1node2.html#Chapter1, in Survey of the State of the Art in Human Language Technology
Ron Cole. Spoken Output Technologies, http://cslu.cse.ogi.edu/HLTsurvey/ch5node2.html#Chapter5, in Survey of the State of the Art in Human Language Technology
Joseph Mariani (ed.). 1999. Multilingual Speech Processing (Recognition and Synthesis), in Multilingual Information Management: Current Levels and Future Abilities. http://www.cs.cmu.edu/people/ref/mlim/index.html
Joseba Abaitua. 2003. Speech-to-speech machine translation An interview with Francisco Casacuberta and Enrique Vidal. Euromap Feature Articles.

Questionnaire 4

Why is information processing a problem?
How much new information is created each year?
How can HLT contribute to solve this problem?
How Intelligent can be Intelligent Text Processing?
Will the semantic web be a solution to the current web situation?

On-line references

Peter Lyman and Hal R. Varian How much information 2003
Jay Branegan and Peggy Salz-Trautman. 1996. Information Fatigue Syndrome
Introduction to Human Language Technologies
Judith Klavans and Eduard Hovy. 1999. Cross-lingual and Cross-modal Information Retrieval Multilingual Information Management: Current Levels and Future Abilities. http://www.cs.cmu.edu/people/ref/mlim/index.html
Semantic Web directory at DELi

Questionnaire 5

We now know that MT is difficult, despite the fact of being the first and more widespread computer-based application related to natural language. This week we are going to learn about MT: history, methods, approaches, best known systems, etc.
1. Which are the most usual interpretations of the term "machine translation" (MT)?
2. What do FAHQT and ALPAC mean in the evolution of MT?
3. List some of the major methods, techniques and approaches
4. Where was MT ten years ago?
5. New directions and foreseeable breakthroughs of MT in the sort term.

On-line references

Machine Translation (MT) is a possible way of overcoming language barriers. However output quality is often a problem. Let us see why.
1. Which are the main problems of MT?
2. Which parts of Linguistics are more relevant for MT?
3. Select two examples of lexical ambiguity
4. Select one example of structural ambiguity
5. Lexical and structural mismatches
6. Collocations
7. Idiomatic expressions
Reference on-line
- Translation problems, by D J Arnold
- Why computers do not translate better, by John Hutchins
- Major Bottlenecks and Problems, by Bente Maegaard
- More examples of collocations, idioms and other lexical mismatches
- The Value of Internet Translation Portals , Jeff Allen, International Journal for Language and Documentation, Issue 6
- The complexity of natural language (ppt)

Questionnaire 6

Computer/Machine aided Translation (CAT or MAT) is an interesting complement to Machine Translation. Many translation professionals view it as an alternative to MT, and they prefer this idea because their role is mantained and their productivity and capacity considerably augmented.
1. How would you describe CAT? Talk about its main functions.
2. What are Translation Memories (TM)? Define TMX and talk of its advantages.
3. Give the reference of at least five TM systems.