Question Answering Systems

The search of answers, called in English Question Answering (QA) is a type of recovery of the information. Given a certain quantity of documents (such as World Wide Web), the system should be capable of recovering answers to questions raised in natural language. QA is observed as a method that needs a technology of Processing of natural language more complex that other types of systems for the Recovery of documents, and, in some cases, it is observed as a step ahead of the technology of the seeker.

A system of question answering is one of the most complex systems concerning the recovery of information. We must bear in mind that a system based on the question-answering is much more difficult than a normal system that entrusts to look for an information in a more or less big quantity of documents, since these it must extract from the above mentioned documents a fragment of (minimal) text that answers to a question given in natural language. These systems are very tied to the seekers web.

A system of question-answering tries to recognize a wide range of types of questions, including facts, lists, definitions, since, when, where, for which, etc. The above mentioned searches can change from small collections of local documents, internal organizations of documents, up to the entire web (or a part of it).

Here we can see a picture of the Question Answering System:

 

 

References:

• Question Answering (2009. In Wikipedia. Retrieved 16:38, May 16, 2009, from: http://en.wikipedia.org/w/index.php?title=Question_answering&oldid=278611780

 

• Sistemas de Question Answering. Retrieved 16:42, May 16, 2009, from: http://question-answering.orgfree.com/

 

• Multilingual Question Answering. Retrieved 15:45, May 16, 2009, from: http://question-answering.orgfree.com/

Natural Language Processing

The Processing of Natural Languages – brief PLN, or NLP- is a subdiscipline of the Artificial Intelligence and the branch engineer of the linguistics computational. The PLN deals with the formulation and investigation of effective mechanisms computationaly for the communication between persons or between persons and machines by means of natural languages. The PLN does not try of the communication by means of natural languages of an abstract form, it tries to design mechanisms to communicate that they should be effective computationaly – that could carry out by means of programs that they execute or simulate the communication-.

The applied models focuses not only on the comprehension of the language of for yes, but on general cognitive human aspects and on the organization of the memory. The natural language uses only as way to study these phenomena.

We should now something of its history:

The Processing of the Natural Language (PLN) is one of the angular early stones of the artificial intelligence (IA). The automatic Translation, for example, was born at the end of the decade of the forties, before there was coined its own expression ” Artificial Intelligence “. Nevertheless, the PLN has recovered multiple roles in the context of the IA, and its importance inside this field has grown and decreased as a result of technological and scientific changes.

The first attempts of translating texts for computer at the end of the forties and during the fifties failed due to the scanty power of the computers and to the scanty linguistic sofistificación. Nevertheless, the efforts realized in the decades of the sixties and the seventies to produce interfaces in natural language for databases and other computer applications obtained a certain significant degree of success. The decade of the eighties and the beginning of that of the nineties have seen the investigation re-arose in the area of the Automatic Translation.

References:

• Natural Languegae Processing (2009) InWikipedia. Retrieved 16:28, April 26, 2009, from: http://en.wikipedia.org/wiki/Natural_language_processing

 

• Natural language processing. Microsoft research site. Retrieved 16:30, April 26, 2009,  from: http://research.microsoft.com/en-us/groups/nlp/

 

• Giovanni Battista Varile, Ronald Cole and Antonio Zampolli (1997). “Survey of the State of the Art in Human Language Technology” . Retrieved 16:32, April 26, 2009, from: http://books.google.es/books?id=WlHD141lKw4C&printsec=frontcover

The XXVth edition of the Annual Congress of the Spanish Society for the Processing of the Natural Language 2009 (SEPLN ‘ 09)

The edition XXV of the Annual Congress of the Spanish Society for the Processing of the Natural Language (SEPLN) Sebastián will be celebrated in Donostia-San Sebastian on the 8th, September 9 and 10, 2009 in Miramar’s Palace.

The Spanish Society for the Processing of the Natural Language (SEPLN) is a non-profit association formed by numerary associates and institutions that were created in the year 1984 in order to promote and to spread all kinds of activities relating to the education, investigation and development in the area of the processing of the natural, both nacional and international language. 

developments in the area of work of the Processing in the Natural Language (PLN) both to the scientific community and to the companies of the place. Also one tries to show the real possibilities of application and to know new projects I+D in this field. In addition, like in previous editions, wants to identify the future directives of the basic investigation and of the applications foreseen by the professionals, in order to confirm them with the real needs of the market. Finally, the congress tries to be a propitious frame to introduce other persons been interested in this area of knowledge.

 

References:

• Sociedad Española para el Procesamiento del Lenguage Natural (2009). Retrieved 15:07, April 21, 2009, from: http://www.sepln.org/

 

• Obejtivos de la Sociedad Española para el procesamiento del Lenguaje Natural (2009). Retrieved 15: 08, April 21, 2009, from: http://www.sepln.org/objetivos.php

 

• XXV. Edición del Congreso Anual de la Sociedad Española para el Procesamiento del Lenguaje Natural (2009). Retrieved 15:09, April 21, 2009, from: http://ixa2.si.ehu.es/sepln2009/

EAMT 09

Europan Elkarteko Itzulpen Automatikoaren hamahirugarren batzarra Diskurtso-zentruaren eta TALP- en eskutik antolatzen ari da eta maiatzaren 14-15 ean ospatuko da Katalunyako Unibertsitate Politeknikoko Nord Kampusan, Bartzelonan, Espainian.

Batzar hauek erabiltzen dira ikertzaileentzat, errebeladore komertzialentzat eta itzulpenarekin eta arlo honekin lotuta dauden erabiltzaileentzat foro bat eskuratzeko. Batzar honen helburuak hurrengo hauek dira:

• Ikerketa berria eta arte arruntaren egoera aurkeztea.

 

• R&D-ren joeren agerpena aztertzea.

 

• Ebaluazio tekniken eta tresnen informazioa hornitzea.

 

• Itzulpenaren eta gobernuaren eta industriaren aldeko itzulpenaren teknologiaren lanpostuen beharrak errepasatzea.

 

Aurtengo aztergai printzipala  ”Europear hizkuntzen arteko itzulpena da, batez ere komunitate linguistiko txikiago duten hizkuntzetarako”.

Gai honi buruz hitz egiteko eta ideak programak bi hizlari aukeratu ditu:

1. Nicholas Ostler (Foundation for Endangered Languages)  

“The Jungle is Neutral” (see abstract)

 

      2.    Lori Levin (Language Technologies Institute, Carnegie Mellon University)

Adaptable, community-controlled, language technologies for language maintenance  (see abstract)

Beraz, animatu eta konferentia honetara etorri!

 

References:

• Conference Venue (2009) In European Association for Machine Translation. Retrieved 14:54, April 15, 2009, from: http://www.talp.cat/eamt09/index.php/conference-venue

 

• The Jungle is Neutral (2009) In European Association for Machine Translation. Retrieved 14:56, April 15, 2009, from: http://www.talp.cat/eamt09/

 

• Adaptable, community-controlled, language technologies, for language maintenance (2009) In European Association for Machine Translation. Retrieved 14:58,April 15, 2009, from: http://www.talp.cat/eamt09/index.php/language-maintenance

 

• 13th Annual Conference of the European Association for Machine Translation (2009) In European Association for Machine Translation. Retrieved 14:59, April 15, 2009, from: http://www.talp.cat/eamt09/

The XXIVth edition of the Annual Congress of the Spanish Society for the Processing of the Natural Language 2008 (SEPLN ‘ 08)

The edition XXIV of the Annual Congress of the Spanish Society for the Processing of the Natural Language (SEPLN) will be celebrated in Leganés (Madrid) on the 10th, September 11 and 12, 2008 in the Technical Top School of the University Carlos III of Madrid

It encourages groups, investigators and companies to send communications, summaries of projects or demonstrations in the area of the technologies of the language in someone of the following thematic areas:

• Linguistic, mathematical and psycholinguistic models of the language

 

• Linguistics of corpus

 

• Extraction and recovery of monolingual and multilingual information

 

• Grammars and formalisms for the morphologic and syntactic analysis

 

• Textual monolingual adn multilingual generation

 

• Automatic translation

 

• Recognition and synthesis of voice

 

• Semantics, pragmatics and speech

 

• Resolution of the lexical ambiguity

 

• Industrial applications of the PLN

 

• Automatic analysis of the textual content

 

Structure of the congress

The duration foreseen of the congress will be three days, with dedicated meetings for the presentation of presentations, as well as to the project presentation of investigation in march or demonstrations of applications prototype or products related to the areas of interest of the congress. 

References:

• Sociedad Española para el Procesamiento del Lenguaje Natural (2009). Retrieved 15:26, April 10, 2009, from: http://www.sepln.org/

 

• Objetivos de La Sociedad Española para el Procesamiento del Lenguaje Natural (2009). Retrieved 15:27, April 10, 2009, from: http://www.sepln.org/objetivos.php

 

• XXIV Edición del Congreso Anual de La Sociedad Española para el Procesamietno del Lenguaje Natural(2009). April 10, April 25, 2009, from: http://basesdatos.uc3m.es/sepln2008/web/programa.html

List of 10 topics mentioned in major sites on Human Language Technologies

1.  Common Language Resources and Technology Infraestructure (CLARIN)

2.  Association for Computational Linguistics (ACLWEB)

3.  Sociedad Española para el Procesamiento del Lenguaje Natural (SEPLN)

4.  European Network of Exellence in Human Language Technologies

5.  National Centre for Language Technology (Ireland)

6.  Edinburgh Language Technology Group (Scotland, UK)

7.  European Chapter of the Association for Computational Linguistics (EACL-09)

8.  Human Language Technologies: The Annual Conference of the North American Chapter of the Association for Computational Linguistics 2007

9.  Annual Meeting of the European Association for Machine Translation

10.  Spell checking (Language Technology World)

References:

The Association for Computational Linguistics (2009). Retrieved 13:13, April 1st, 2009, from: http://www.aclweb.org/

Sociedad Española para el Procesamiento del Lenguaje Natural. Retrieved 13:23, April 1st, 2009, from: http://www.sepln.org/

National Centre for Language Technology. Dublin City University, Ireland. Retrieved 12:18, April 1st, 2009, from: http://www.nclt.dcu.ie/

The Stanford Natural Language Processing Group. Standford University. Retrieved 12:09, April 1st, 2009, from: http://nlp.stanford.edu/

13th Annual Conference of the European Association for Machine Translation. EAMT (2009). Retrieved 12:24, April 1st, 2009, from: http://www.talp.cat/eamt09/

Martin Kay

Martin Kay es un informático conocido sobre todo para su trabajo en la lingüística computacional. Nacido y crecido en Gran Bretaña, él recibió su M.A. del Colegio de Trinidad, Cambridge, en 1961. En 1958 él comenzó a trabajar en la Unidad de Investigación de Lengua de Cambridge, uno de los centros más tempranos para la investigación en que ahora saben(conocen) como la Lingüística Computacional.

En 1961 se movió a la Corporación de Rand en Santa Mónica, California, donde tarde o temprano se hizo el jefe de la investigación en la lingüística y la traducción automática. Abandonó el Rand en 1972 para hacerse con la Silla del Departamento de Informática en la Universidad de California, Irvine. En 1974 movió a Xerox Palo Alto el Centro de investigación como un Muchacho de Investigación. En 1985, conservando su posición en Xerox PARC, unió la facultad de media jornada de Universidad de Stanford.  Es actualmente el Profesor de Lingüística en la Universidad de Stanford y el Profesor Honorario de Lingüística Computacional en la Universidad Saarland.

Sus logros incluyen el desarrollo de análisis de carta y la gramática de unificación funcional y contribuciones principales al uso de autómatas finitos estatales en la fonología computacional y la morfología. También es considerado como una autoridad principal sobre la traducción automática.

Sus honores incluyen un Doctor honorario en la Filosofía de la Universidad Gothenburg y la Asociación 2005 para el Premio de Logro De la vida de la Lingüística Computacional. Es el presidente permanente del Comité Internacional contra la Lingüística Computacional.

References:

Martin Kay. Wikipedia (2008). Retrieved 12:59, March 9, 2009, from: http://en.wikipedia.org/wiki/Martin_Kay

Cambridge Language Research Unit. Wikipedia (2008). Retrieved 13:00, March 9, 2009, from: http://en.wikipedia.org/wiki/Cambridge_Language_Research_Unit

International Committee on Computational Linguistics. Wikipedia (2008). Retrieved 13:02, March 9, 2009, from: http://en.wikipedia.org/wiki/International_Committee_on_Computational_Linguistics

Functional Unification Grammar. Wikipedia (2008). Retrieved 13:03, March 9, 2009, from: http://en.wikipedia.org/wiki/Functional_unification_grammar