Sarean Zer? Interneteko berriak lo tzeko baliabidea

Hernández, Gregorio . Sarean Zer? Interneteko berriak lo tzeko baliabidea., 2009 In: Dokumentazio zerbitzuak Euskal Herriko komunikabideetan = Los servicios de documentación en los medios de comunicación del País Vasco. Euskal Herriko Unibertsitatea = Universidad del País Vasco, pp. 113-120. [Book chapter]

[img]
Preview
PDF
6.pdf

Download (180Kb) | Preview

English abstract

“Sarean Zer?” (What’s new on the web?) A resource for associating news on the Internet. The various classes of information that can be found on the Internet have no relationship, that is, they are not well organised as far as multiple use is concerned. For this reason, when we want to gain access to information from a general point of view of semantics, we find that it is impossible. The product which goes by the name of “Sarean Zer?” aims to tackle this problem in the field of digital newspapers by relating the news published in different newspapers.

Basque abstract

Interneten bidez hedatzen diren mota desberdinetako informazioek ez daukate elkarren arteko erlaziorik, hau da, erabilera askori begira ez daude ondo antolatuta. Horregatik, informazioa ikuspegi semantiko orokor batetik atzitu nahi dugunean ezinezkoa gertatzen zaigu. Sarean Zer? izeneko produktuak arazo horri aurre egin nahi dio egunkari digitalen esparruan. Bere helburua egunkari desberdinek argitaratutako albisteak lotzea da.

Item type: Book chapter
Keywords: Crosslingual,Information retrieval, Semantic search, Natural language processing, Newspapers, Recuperación de la información, Búsqueda semántica, Procesamiento del lenguaje natural, Prensa, Periódicos.
Subjects: L. Information technology and library technology. > LM. Automatic text retrieval.
Depositing user: Teresa Agirreazaldegi
Date deposited: 10 Jun 2011
Last modified: 02 Oct 2014 12:19
URI: http://hdl.handle.net/10760/15784

References

"SEEK" links will first look for possible matches inside E-LIS and query Google Scholar if no results are found.

[1] Modern Information Retrieval. Ricardo Baeza-Yates, Berthier Ribeiro-Neto. Addison-Wesley. 1999.

[2] CLIR: Cross-language information retrieval. G Grefenstette-Kluver, Boston, 1998.

[3] B.MATHIEU, R.BESANÇON, C.FLUHR, «Multilingual document clusters discovery», RIAO 2004, Avignon, France, April 26-28, 2004.

[4] KHALED M. HAMMOUDA «Efficient Phrase-based document indexing for web document clustering».

[5] TIM LEEK, HUBERT JIN, SREENIVASA, RICHARD SCHWAR TZ «The BBN crosslingual topic detection and tracking system», BBN Technologies, MA.

[6] RALF STEINBERGER, BRUNO POULIQUEN, JOHAN HAGMAN, «Crosslingual Document Similarity Calculation Using the Multilingual Thesaurus EUROVOC» (2002).

[7] EUROWORDNET: a multilingual database with lexical semantic networks. P Vossen-Norwell, MA: Kluwer Academic Publishers, 1998.

[8] NICOLA STOKES, JOE CARTHY, «Combining Semantic and Syntactic Document Classifiers to improve First Story Detection», Department of Computer Science, University College Dublin, Ireland.

[9] S. T. DUMAIS, T. A. LE TSCHE, M. L. LITTMAN, AND T. K. LANDAUER. Automatic cross-language retrieval using latent semantic indexing. Working notes of AAAI Spring Symposium on Cross-Language Text and Speech Retrieval, 1997.


Actions (login required)

View Item View Item