This paper will address the debate existing between promoters of the Semantic Web [1] and NLP oriented practitioners of the web like us but in particular we will be referring to the creators of the START QA system [6]: the former believe that by simply establishing a standard in the format of the information to be published on the web they will allow natural language communication, i.e. question/answering, to ensue. On the contrary, practitioners of the web find it totally misleading and insufficient in itself: they assume that natural language facilities must come first. This debate is reminiscent of a similar debate existing between people working in the NLP paradigm who have witnessed an increasing gap dividing on the one side, Knowledge Representation oriented researchers – usually engineers, their implementations being some variant of expert systems; on the other side, NLP oriented computational linguists who have continued working within the domain of a syntactic-semantic approach, not disregarding the relevance of knowledge of the world, but trying to reduce its impact on the overall architecture of a Text/Speech Understanding System.

Semantic Web, RDFs and NLP for QA

DELMONTE, Rodolfo;
2003-01-01

Abstract

This paper will address the debate existing between promoters of the Semantic Web [1] and NLP oriented practitioners of the web like us but in particular we will be referring to the creators of the START QA system [6]: the former believe that by simply establishing a standard in the format of the information to be published on the web they will allow natural language communication, i.e. question/answering, to ensue. On the contrary, practitioners of the web find it totally misleading and insufficient in itself: they assume that natural language facilities must come first. This debate is reminiscent of a similar debate existing between people working in the NLP paradigm who have witnessed an increasing gap dividing on the one side, Knowledge Representation oriented researchers – usually engineers, their implementations being some variant of expert systems; on the other side, NLP oriented computational linguists who have continued working within the domain of a syntactic-semantic approach, not disregarding the relevance of knowledge of the world, but trying to reduce its impact on the overall architecture of a Text/Speech Understanding System.
2003
Temi e prospettive di ricerca per l’elaborazione del linguaggio naturale in Italia -Topics and Research Perspectives for Natural Language Processing in Italy
File in questo prodotto:
File Dimensione Formato  
semweb-rd.pdf

non disponibili

Tipologia: Abstract
Licenza: Licenza non definita
Dimensione 206.27 kB
Formato Adobe PDF
206.27 kB Adobe PDF   Visualizza/Apri

I documenti in ARCA sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10278/39507
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact