Questionnaire #3: Machine translation

Machine translation, sometimes referred to by the abbreviation MT, is a sub-field of computational linguistics that investigates the use of computer software to translate text or speech from one natural language to another. At its basic level, MT performs simple substitution of words in one natural language for words in another. Using corpus techniques, more complex translations may be attempted, allowing for better handling of differences in linguistic typology, phrase recognition, and translation of idioms, as well as the isolation of anomalies.

Today a number of systems are available which produce output which, if not perfect, is of sufficient quality to be useful for certain specific applications, usually in the domain of technical documentation. In addition, translation software packages which are designed primarily to assist the human translator in the production of translations are enjoying increasingly popularity within professional translation organizations.

These are some examples of Online transaltors:

• OpenTrad, http://www.opentrad.org/demo
• Systran, http://oesi.cervantes.es/traduccionAutomatica.html (complemented by ATS)
• ProMT, http://elmundo.reverso.net/textonly/default.asp (aka Reverso)
• Lucy, http://www.translendium.net:8080/home/ (aka Translendium, Metal)
• Google, http://translate.google.com/

Languages from the world

References:

• Machine translation. (2009, March 26). In Wikipedia, The Free Encyclopedia. Retrieved 09:56, April 1, 2009, from http://en.wikipedia.org/w/index.php?title=Machine_translation&oldid=279707378
• Definition of Machine Translation. In Macalester College. Retrieved 12:14. April 4. From http://www.macalester.edu/courses/russ65/definiti.htm

Questionnaire #3: Question answering systems

Related with the topic below this post is going to be related with one of the most developed systems: the question answering.  As in the post below I developed abut how does they work, in this I am just going to give few examples of them.

• Powerset: Powerset’s goal is to change the way people interact with technology by enabling computers to understand our language Powerset’s first product is a search and discovery experience for Wikipedia, launched in May 2008. Powerset’s technology improves the entire search process. In the search box, you can express yourself in keywords, phrases, or simple questions. On the search results page, Powerset gives more accurate results, often answering questions directly.
• Anna: If you have any doubts with IKEA, you can ask her. Although she is not very developed she can redirect you to any part in IKEA’s web page in order to get any products.
• Answers.com: This works as Power Set does.

Ask Anna if you have any doubts on IKEA

References

• About Powerset. In Powerset. Retrieved April 1st 11:15. From: http://www.powerset.com/about
• ¿Necesitas ayuda? In IKEA. Retreieved 11:23 April 1st. In: http://www.ikea.com/ms/es_ES/customer_service/splash.html
• Question answering. (2009, March 20). In Wikipedia, The Free Encyclopedia. Retrieved 09:47, April 1, 2009, from http://en.wikipedia.org/w/index.php?title=Question_answering&oldid=278611780

Questionnaire #2: Answer Extraction

The system takes a natural-language query as input and produces a list of  answers ranked in order of confidence. According to Language Techonology World where a project in Answer Extraction is developed by  Rolf Schwitter, Michael Hess, Rachel Fournier, Diego Mollá-Aliod, Gerold Schneider, ExtrAns is one of the most developed programs in Answer Extraction.

ExtrAns is a system that finds answers to questions about (the Solaris variety of) UNIX in the on-line system documentation, the manpages. The questions may be phrased in ordinary English rather than in some formal query language. The answers are the sentence(s) of the manpages containing direct answers to the question (if there are any), complete with clickable links into the full manpages containing them.

The search procedure uses a proof algorithm of the user query over the Horn clause representation of the minimal logical forms. Remaining ambiguities in the retrieved sentences are dealt with by graded highlighting.

References:

• ExtrAns.  In Zurich university.  Retrieved 30th March 2009, 12:15. From http://www.ifi.uzh.ch/arvo/cl/extrans/
• Answer Extraction by Steven Abney Michael Collins Amit Singhal. In Vinartus Retrieved 30th March 2009, 12:35. From http://www.vinartus.net/spa/99f.pdf
• Extrans, an answer extraction system by Mots Clefs Keywords, Diego Moll, Diego Moll, Rolf Schwitter, Rolf Schwitter, Michael Hess, Michael Hess, Rachel Fournier, Rachel Fournier. In CtiteSeer. Retrieved 30th march 2009, 12:45. From http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.43.3993
• Off-line Answer Extraction for Dutch Question Answering (December 17th 2004) In Odur by Jori Mur. retrieved 30th March 2009, 12:50. From http://odur.let.rug.nl/~gosse/Imix/clin04_mur.pdf

Questionnaire #2: Emotion Recognition

The new trends in human-computer interfaces, which have evolved from conventional mouse and keyboard to automatic speech recognition systems and special interfaces designed for disabled people, do not take complete advantage of these valuable communicative abilities, resulting often in a less than natural interaction.

Facial expressions are privileged relative to other nonverbal “channels” of communication, such as vocal inflections and body movements. Facial expressions appear to be the most subject to conscious control. The ability to recognize emotion from facial expressions appears at least partially inborn. Newborns prefer to look at faces rather than other complex stimuli, and thus may be programmed to focus on information in faces. Until now the most widely used speech cues for audio emotion recognition are global-level prosodic features such as the statistics of the pitch and the intensity.

As Lisa Feldman Barrett, Peter Salovey, John D. Mayer pint out, several aspects should be taken into account in facial recognition: such as: gender, socioesconomic status,  personality, age… That all make facial emotion recognicion so difficult.

Emotions

Resources:

• Analysis of Emotion Recognition using Facial Expressions, Speech and Multimodal Information by Carlos Busso, Zhigang Deng, Serdar Yildirim, Murtaza Bulut, Chul Min Lee, Abe Kazemzadeh, Sungbok Lee, Ulrich Neumann, Shrikanth Narayanan. In .doc stock. Retrieved Wednesday 25th March 2009, 12:15. From: http://www.docstoc.com/docs/2373058/Analysis-of-Emotion-Recognition-using-Facial-Expressions-Speech
• The Wisdom in Feeling (2002) by Lisa Feldman Barrett, Peter Salovey, John D. Mayer. In Google Books. Retreievd 28 MArch 2009, 17:10. From http://books.google.es/books?id=qoUddTKwZ6IC&printsec=frontcover&dq=The+Wisdom+in+Feeling More information about the book: http://books.google.es/books?id=qoUddTKwZ6IC&dq=The+Wisdom+in+Feeling&source=gbs_summary_s&cad=0
  

Questionnaire #2: The intelligent Library Assistant

In modern society, robots are been designed to play an increasing role in the lives of ordinary people. Among the emerging areas in robotics is the field of service robots. One example of it is an intelligent library assistant robot.

Universities and some public libraries use a kind of intelligent Library Assistant to search for the books, and categorize them. Now,  This work in progress towards a complete system working to assist users on a library. With this aim, the system must be capable  of looking for a specific book in a shelf, asked by any user,and  deliver it as soon as possible to the user.

The proyect developing now by the German Research Center for Artificial Intelligence has got the following aims according to his manager, Norbert Reithinger:

• Investigation, supply and adaptation of the contents of a real digital library for interactive information extraction
• Hybrid information extraction based on a combination of metadata and document processing
• Development of domain-adaptive deep methods for information extraction using the example of biomedical documents
• Prototypical development of interactive personalized navigation allowing the user of the digital library an intuitive multimodal search

References:

• The development of an intelligent library assistant robot (2006) by Julie Behan and Derek T. O’Keeffe, in Portal. Retrieved March 24, 19:35. In http://portal.acm.org/citation.cfm?id=1166971
• An Autonomous Assistant Robot For Book Manipulation in a Library by Ramos-Garijo R, Prats M, Sanz PJ, Del Pobil AP. In Robot intelligence Lab. retrieved March 25th, 11:25. From: http://www.robot.uji.es/people/mprats/jaume/SMC03.pdf
• The intelligent Library Assistant. Project managed by Norbert Reithinger In German Research Center for Artificial Intelligence. Retrieved March 25th, 11:45- From: http://www.dfki.de/lt/project.php?id=Project_447&l=en

Note: Updated, 28th March 2009 (16:41)

Questionnaire #2: List of topics

Here there are the topics I have chosen.

1. The intelligent Library Assistant
2. Answer Extraction
3. Morphological Analysis
4. Lexical-Functional Grammar
5. Sustained Emotionally coloured Machine-human Interaction using Nonverbal Expression
6. Citizens Advanced Relationship Management
7. Intelligent dialogue control and expressive speech synthesis for computer games
8. Emotion Recognition
9. Text-to-speech Synthesis
10. Automatic Language Identification

Resources:

• Projects. In Language technology world. Retrieved 23th March 2009, 12:42 from: http://www.lt-world.org/
• Completed Projects. In German research center of Artificial Intelligence. Retrieved 23th March 2009, 12:45 from: http://www.dfki.de/lt/completed_projects.php
• Current Projects. In German research center of Artificial Intelligence. Retrieved 23th March 2009, 12:47 from: http://www.dfki.de/lt/current_projects.php

Questionnaire #1: Europe’s Human Language Technology Research Centers

1. University of Trento

As their own web page defin the course they impart:

Human language technology (HLT) is becoming increasingly essential to analyze, understand and exploit the huge amounts of information currently available in the form of web, textual or spoken documents. HLT gives people the possibility of using speech and/or natural language to interact to conversational machines and support advanced services. Service and technology providers are therefore strong supporters of this technology. The Master in Human Language Technology and Interfaces aims at providing skills in the basic theories, algorithms, and applications of this technology through courses taught by internationally recognized researchers from the university, research centers and supporting industry partners. This master is aimed both to students seeking advanced education to pursue a career in the HLTI industry or research track (e.g. PhD). Educational credits gained completing this program can be partly recognized to students afterwards admitted to the ICT International Doctoral School.

2. European Network of Excellence in Human Language Technologies

ELSNET is a Europe-based forum dedicated to human language technologies. It operates in an international context, and will consider, across discipline limits, all human communication research areas related to speech and language.

ELSNET aims to advance R&D in human language technologies in Europe by bringing together the key players in the field, and by providing a proactive, open forum which will serve as different purposes such as: a platform for launching innovative actions, a platform for making analyses of the present, and developing visions for the future or a platform for fostering a common environment, comprising resources, standards and evaluation.

3.  German Research Center of Artificial Intelligence

As they say about theirselves:

Our mission is the improvement of language technology through novel computational techniques for processing text, speech and knowledge, a deeper understanding of human language and thought, studying the true needs of the end user and the demands of the market

We develop novel and improved applications in three areas: Information and Knowledge Management. Document Production, Natural Communication

One of our commercial activities is indexing of German and English texts using the IDX software package.

References.

• International Master in Human Language Technology and Interfaces. From University of Trento. Retrieved 7 March, 2009, 14:02 In: http://old.disi.unitn.it/disi/edu/hlti/home.xml
• About us. From European Network of Excellence in Human Language technologies.Retrieved 7, March 2009, 14:39. In: http://www.elsnet.org/about.html?table
• Language Technology Lab. In General research center of Artificial Intelligence. Retrieved 7, March 2009: 15:21. In: http://www.dfki.de/lt/

Questionnaire #1: Yorik Wilks. Short biography.

Yorick Wilks was borned in 1939, he was educated at Pembroke College, Cambridge and was an early pioneer in meaning-based approaches to the understanding of natural language content by computers. Since the early 70s he has worked in several research projects all over in convination with being proffesor the world: California, Switzerland, Edinburg, Essex, Sheffield, and finally Oxford.  His interests are artificial intelligence and the computer processing of language, knowledge and belief, and his recent books shows a development of those researches such as: Digital Technologies Shaping e-Research, The Semantic Web and the Apotheosis of annotation. In Proceedings of IEEE Information Systems.and Cross Domain Dialogue Act Tagging. In Proceedings of the 6th International Conference on Language, Resources and Evaluation… His work has been so congratulated that we can find the following awards in his career since its early beginning:

• 2008 Zampolli Prize (ELDA, awarded at LREC-08 in Marrakech, Morocco)
• 2008 Lifetime Achievement Award (ACL, awarded at ACL-08 in Columbus, OH)
• 2006 Visiting Professor, University of Oxford (2006-)
• 2004 Elected to UK Computing Research Council
• 2004 Elected fellow, British Computer Society
• 2003 Visiting Fellow, Oxford Internet Institute
• 1998 Elected Fellow of European Association for Artificial Intelligence
• 1997 Elected Fellow, EPSRC College of Computing
• 1991 Visiting Fellow, Trinity Hall, Cambridge.
• 1991 Elected Fellow of the American Association for Artificial Intelligence
• 1983 Royal Society Travel Fellowship
• 1983 Commonwealth of Australia Visiting Professor
• 1981 Visiting Sloan Fellow, University of California, Berkeley
• 1980 Invited Participant in the Nobel Symposium on Language, Stockholm
• 1979 NATO Senior Scientist Fellowship
• 1979 Visiting Sloan Fellow, Yale University
• 1975 SRC Senior Visiting Fellowship, University of Edinburgh

Yorick Wilks

References:

• Yorick Wilks. (2009, January 4). In Wikipedia, The Free Encyclopedia. Retrieved 20:21, March 4, 2009, from http://en.wikipedia.org/w/index.php?title=Yorick_Wilks&oldid=261889889
• Yorick Wilks. In The University of Sheffield. Retrieved 20:31, March 4, 2009, from http://www.dcs.shef.ac.uk/~yorick/cv.html
• Yorick Wilks. In Oxford Internet Institute. Retrieved 20:44, March 4, 2009, from http://people.oii.ox.ac.uk/yorick/

Questionnaire #1: Human Language Technologies, definitions.

According to a survey published by Cambridge University Press and Giardini:

Human Language Technologies are a very important way of communication as languages are, above all, the first way of communication all over the world. In addition with the help that globalization has provided Language technology offers people the opportunity to improve their communication. The ability to exchange communicative messages with the comoputers have been serached by many engineers and scholars. Hawever, the Human Language Technologies has got very difficult problems to create them such as Speaking Mode, speaking style, enrollment or language model to name some.

As CORDIS, an European Centre of Investigation in Human language tachnologies, defines HLT are:

The overall objective of HLT is to support e-business in a global context and to promote a human centred infostructure ensuring equal access and usage opportunities for all. This is to be achieved by developing multilingual technologies and demonstrating exemplary applications providing features and functions that are critical for the realisation of a truly user friendly Information Society. Projects address generic and applied RTD from a multi- and cross-lingual perspective, and undertake to demonstrate how language specific solutions can be transferred to and adapted for other languages.

References:

• Survey of the State of the Art in Human Language Technology (1997) In German Research Center of Artificial Intelligence. Retrieved 12:02, March 2nd 2009. From http://www.dfki.de/~hansu/HLT-Survey.pdf
• Human Language Technologies. In Cordis Europe. Retrieved 28th March 2009, 16:01. From: http://cordis.europa.eu/ist/ka3/hlt.htm
• Human Language Technologies for Knowledge Management: Challenges and Opportunities (by Mark Maybury) In information Technologies Delivery. retrieved 13:03, March 2nd 2009. From http://delivery.acm.org/10.1145/1120000/1118222/p2-maybury.pdf?key1=1118222&key2=6938995321&coll=GUIDE&dl=GUIDE&CFID=24258607&CFTOKEN=63055578

Note: This post has been updated on Saturday 28th March 2009 (16:22)