Loading presentation...

Present Remotely

Send the link below via email or IM

Copy

Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.

DeleteCancel

Semiautomated recognition and semantic annotation of Italian lemmas exploiting multilingual WordNet

Knowledge Representation Lab 2009-2010
by

Tommaso Soru

on 30 April 2010

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of Semiautomated recognition and semantic annotation of Italian lemmas exploiting multilingual WordNet

Semiautomated recognition
and semantic annotation
of Italian lemmas
exploiting multilingual WordNet PAC
database ________________________________________________ MultiWordNet WordNet 1.6 WordNet 3.0 Lemma recognition Word Mapping Sense mapping Application RDF XHTML WordNet querying Web application ___________________________________________________________ get all concepts
get all relations
get all attributes lemma get expression similar to lemma words' ID
in WordNet get words'
information words' ID
in WordNet words'
information words'
information words'
semantic
information words'
syntactic
information Bibliography Aim of the project is to link some linguistic data to the semantic web, using W3C recommended notation. The original language is Italian and data comes from the Public Administration Catalog. A Java based tool - developed in the context of a related project - tries to extract semantics from the lemmas used in the catalog and maps them on MultiWordNet, a multilingual version of WordNet. Relations between lemmas are stored into RDF documents, following the rules of a OWL ontology. The content could be also human-readable, by embedding metadata within web documents, using RDFa and XHTML. Abstract State of the Art WordNet
an English lexical database (Princeton University) MultiWordNet
a multilingual version
(Università di Trento) ___________ English
Lemma Italian
Lemma 1...N 1...N ItalWordNet
(CNR, Pisa) NON-FREE
LICENSE translation Lemma versus Word ___________ English
Word Italian
Word 1...N 1...N translation _________ 1 1...N ◊ ∆ ∆ ___________ ______ _____________________ ___________ ______ _____________________ The translation problem W3C
Standards (p,e) (p,e) Tommaso Soru
t.soru@campus.unimib.it
Full transcript