W3C home > Mailing lists > Public > public-lod@w3.org > July 2012

Re: New releases - FRED and Tipalo: from natural language to RDF/OWL

From: Aldo Gangemi <aldo.gangemi@cnr.it>
Date: Thu, 12 Jul 2012 20:22:30 +0200
Cc: Aldo Gangemi <aldo.gangemi@cnr.it>, valentina presutti <vpresutti@gmail.com>, public-lod@w3.org, "Norbert E. Fuchs" <fuchs@ifi.uzh.ch>
Message-Id: <9F9ED3AF-12C6-4DB9-BE7F-A85DB56A60F8@cnr.it>
To: Jean-Marc Vanel <jeanmarc.vanel@gmail.com>
I like ATTEMPTO, but we are talking about two different pipelines here: ACE is a controlled natural language, from which you can produce DRS and RDF, while FRED takes any natural language sentence, and outputs RDF passing through DRS produced by Boxer. 

The two situations are deeply different: of course, the more controlled a NL sentence is, the more predictable are the parses and the design of RDF or OWL from them. However, accuracy obtained from controlled natural languages requires people to contain themselves when writing, and existing documentation cannot be reused.

Wild sentences such as those from tweets are often too cumbersome to be digested by deep parsing, but average NL from e.g. news, reports, scientific papers can be parsed with good results.

--Aldo

On 12 Jul 2012, at 17:41, Jean-Marc Vanel wrote:

> I took some notes while trying FRED :
> http://deductions-software.blogspot.fr/2012/07/trying-fred-tool-for-producing-rdfowl.html
> 
> FRED is a nice tool, but ATTEMPTO [1] is still more accurate when it
> comes to real logic based sentences.
> 
> [1]  ATTEMPTO http://attempto.ifi.uzh.ch/site/description/
> 
> 2012/7/12 valentina presutti <vpresutti@gmail.com>:
>> Dear all,
>> 
>> We are pleased to announce the release of two new tools: FRED and Tipalo. Online demonstrators are available from the STLab tools page [0] that collects our software releases. We invite you to play with them, and provide your welcome feedback:
>> 
>> FRED - http://wit.istc.cnr.it/stlab-tools/fred
>> A tool for automatically producing RDF/OWL ontologies and linked data from natural language sentences, currently limited to English.
>> FRED is based on C&C [1] and Boxer [2], a NLP tool that transforms natural language text into a logical form compliant to Discourse Representation Theory. We process Boxer output and apply a set of heuristics and semantic transformations in order to obtain RDF designed for the Semantic Web. In this process, we emphasize the relation to linguistic frames, supporting FrameNet and VerbNet vocabularies, and to ontology design patterns.
>> In order to further improve interlinking of FRED results with LOD, a number of features are under testing (they are already available in the Tipalo tool), including Named Entity Resolution (based on Apache Stanbol [3]) and Word Sense Disambiguation (based on UKB [4]). FRED results are available as n-triples or graphs. A paper on FRED will be presented at next EKAW2012 [5].
>> 
>> Tipalo - http://wit.istc.cnr.it/stlab-tools/tipalo
>> A tool that automatically assigns types to Wikipedia entities in a LOD-intensive graph. Given a Wikipedia page URI, the tool returns a RDF graph composed of rdf:type, rdfs:subClassOf, owl:sameAs, and owl:equivalentTo statements providing typing information (organized into class taxonomies) about the entity referred by the Wikipedia page. Currently, entity types are derived from the text, and aligned to the DBpedia Ontology [6], WordNet 3.0 in RDF [7], DUL [8], and DolceZero [9]. The tool relies on FRED (including NER and WSD), hence it has unlimited domain coverage (i.e., it is independent from the completeness of specific ontologies). Results are available as RDF, HTML (with LODE [10]), and graphs. A paper describing Tipalo is currently under review.
>> 
>> Each tool is described in more detail in dedicated documentation.
>> 
>> Enjoy!
>> 
>> Feedback welcome to stlab@cnr.it
>> 
>> The STLab team [11]
>> 
>> Designers and developers of Tipalo and FRED are: Aldo Gangemi, Valentina Presutti, Francesco Draicchio, Alberto Musetti, Andrea Nuzzolese
>> 
>> This work has been partly supported by EU IKS project [12] and developed in collaboration with the Computer Science department of the University of Bologna [13].
>> 
>> [0] http://with.isct.cnr.it/stlab-tools/
>> [1] http://svn.ask.it.usyd.edu.au/trac/candc
>> [2] http://svn.ask.it.usyd.edu.au/trac/candc/wiki/boxer
>> [3] http://incubator.apache.org/stanbol/
>> [4] http://ixa2.si.ehu.es/ukb/
>> [5] http://ekaw2012.ekaw.org/node/137
>> [6] http://dbpedia.org/Ontology
>> [7] http://semanticweb.cs.vu.nl/lod/wn30/
>> [8] http://www.ontologydesignpatterns.org/ont/dul/DUL.owl
>> [9] http://www.ontologydesignpatterns.org/ont/d0.owl
>> [10] http://www.essepuntato.it/lode
>> [11] http://stlab.istc.cnr.it/stlab/People
>> [12] http://iks-project.eu/
>> [13] http://www.informatica.unibo.it/
> 
> 
> 
> -- 
> Jean-Marc Vanel
> Déductions SARL - Consulting, services, training,
> Rule-based programming, Semantic Web
> http://deductions-software.com/
> +33 (0)6 89 16 29 52
> chat :  irc://irc.freenode.net#eulergui
> 



_____________________________________

Aldo Gangemi
Senior Researcher
Semantic Technology Lab (STLab)
Institute for Cognitive Science and Technology,
National Research Council (ISTC-CNR) 
Via Nomentana 56, 00161, Roma, Italy 
Tel: +390644161535
Fax: +390644161513
aldo.gangemi@cnr.it
http://www.stlab.istc.cnr.it
http://www.istc.cnr.it/people/aldo-gangemi
skype aldogangemi
okkam ID: http://www.okkam.org/entity/ok200707031186131660596
Received on Thursday, 12 July 2012 18:23:25 UTC

This archive was generated by hypermail 2.3.1 : Sunday, 31 March 2013 14:24:41 UTC