We present a system for Question Answering which computes a prospective answer from Logical Forms (hence LFs) produced by a full-fledged NLP for text understanding, and then maps the result onto schemata in SPARQL to be used for accessing the Semantic Web. As an intermediate step, and whenever there are complex concepts to be mapped, the system looks for a corresponding amalgam in YAGO classes. This is what happens in case the query to be constructed has [president,'United States'] as its goal, and the amalgam search will produce the complex concept [PresidentOfTheUnitedStates]. In case no class has been recovered, as for instance in the query related to the complex structure [5th,president,'United States'] the system knows that the cardinal figure '5th' behaves like a quantifier restricting the class of [PresidentOfTheUnitedStates]. In fact LFs are organized with a restricted ontology made up of 7 types: FOCus, PREDicate, ARGument, MODifier, ADJunct, QUANTifier, INTensifier, CARDinal. In addition, every argument has a Semantic Role to tell Subject from Object and Referential from non-Referential predicates. Another important step in the computation of the final LF, is the translation of the interrogative pronoun into a corresponding semantic class word taken from general nouns, in our case the highest concepts of WordNet hierarchy. The result is mapped into classes, properties, and restrictions (filters) as for instance in the question: Who was the wife of President Lincoln ? which becomes the final LF: be-[focus-person, arg-[wife/theme_bound], arg-['Lincoln'/theme-[mod-[pred-['President']]]]] and is then turned into the SPARQL expression, ?x dbpedia-owl:spouse :Abraham_Lincoln where "dbpedia-owl:spouse" is produced by searching the DBpedia properties and in case of failure looking into the synset associated to the concept as WIFE. In particular then, the concept "Abraham_Lincoln" is derived from DBpedia by the association of a property and an entity name, "President" and "Lincoln", which contextualizes the reference of the name to the appropriate referent in the world. It is just by the internal structure of the Logical Form that we are able to produce a suitable and meaningful context for concept disambiguation. Logical Forms are the final output of a complex system for text understanding - GETARUNS - which can deal with different levels of syntactic and semantic ambiguity in the generation of a final structure, by accessing computational lexical equipped with sub-categorization frames and appropriate selectional restrictions applied to the attachment of complements and adjuncts. The system also produces pronominal binding and instantiates the implicit arguments, if needed, in order to complete the required Predicate Argument structure which is licensed by the semantic component.

Linguistically Based QA by Dinamyc LOD Access from Logical Form

TRIPODI, ROCCO;DELMONTE, Rodolfo
2011-01-01

Abstract

We present a system for Question Answering which computes a prospective answer from Logical Forms (hence LFs) produced by a full-fledged NLP for text understanding, and then maps the result onto schemata in SPARQL to be used for accessing the Semantic Web. As an intermediate step, and whenever there are complex concepts to be mapped, the system looks for a corresponding amalgam in YAGO classes. This is what happens in case the query to be constructed has [president,'United States'] as its goal, and the amalgam search will produce the complex concept [PresidentOfTheUnitedStates]. In case no class has been recovered, as for instance in the query related to the complex structure [5th,president,'United States'] the system knows that the cardinal figure '5th' behaves like a quantifier restricting the class of [PresidentOfTheUnitedStates]. In fact LFs are organized with a restricted ontology made up of 7 types: FOCus, PREDicate, ARGument, MODifier, ADJunct, QUANTifier, INTensifier, CARDinal. In addition, every argument has a Semantic Role to tell Subject from Object and Referential from non-Referential predicates. Another important step in the computation of the final LF, is the translation of the interrogative pronoun into a corresponding semantic class word taken from general nouns, in our case the highest concepts of WordNet hierarchy. The result is mapped into classes, properties, and restrictions (filters) as for instance in the question: Who was the wife of President Lincoln ? which becomes the final LF: be-[focus-person, arg-[wife/theme_bound], arg-['Lincoln'/theme-[mod-[pred-['President']]]]] and is then turned into the SPARQL expression, ?x dbpedia-owl:spouse :Abraham_Lincoln where "dbpedia-owl:spouse" is produced by searching the DBpedia properties and in case of failure looking into the synset associated to the concept as WIFE. In particular then, the concept "Abraham_Lincoln" is derived from DBpedia by the association of a property and an entity name, "President" and "Lincoln", which contextualizes the reference of the name to the appropriate referent in the world. It is just by the internal structure of the Logical Form that we are able to produce a suitable and meaningful context for concept disambiguation. Logical Forms are the final output of a complex system for text understanding - GETARUNS - which can deal with different levels of syntactic and semantic ambiguity in the generation of a final structure, by accessing computational lexical equipped with sub-categorization frames and appropriate selectional restrictions applied to the attachment of complements and adjuncts. The system also produces pronominal binding and instantiates the implicit arguments, if needed, in order to complete the required Predicate Argument structure which is licensed by the semantic component.
2011
Proceedings of the Internazional Conference on Knowledge Engineering and Ontology Development
File in questo prodotto:
File Dimensione Formato  
36291.pdf

accesso aperto

Tipologia: Documento in Post-print
Licenza: Accesso gratuito (solo visione)
Dimensione 337.34 kB
Formato Adobe PDF
337.34 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/10278/28820
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact