230 likes | 358 Views
ORAKEL: A Natural Language Interface to an F-Logic Knowledge Base. Philipp Cimiano Institute AIFB University of Karlsruhe. NLDB 2004. Outline. Aim & Scope System Architecture F-Logic in a Nutshell Semantic Construction Component Lexicon Generation Component Conclusion & Further Work.
E N D
ORAKEL: A Natural Language Interface to an F-Logic Knowledge Base Philipp Cimiano Institute AIFB University of Karlsruhe NLDB 2004
Outline • Aim & Scope • System Architecture • F-Logic in a Nutshell • Semantic Construction Component • Lexicon Generation Component • Conclusion & Further Work
Aims & Scope • Aim: accessing a KB via natural language • translating language into logical queries • Who owns a company? • Who owns every company? • Who does not own a company? • Scope: • consider only factoid questions • simple syntactic structure: SVO +PP?
Parsing + Sem. Construction General Lexicon NL query logical query Domain Lexicon answer Lexicon Generation Ontobroker F-Logic KB System Architecture
F-Logic in A Nutshell • frames/methods: microsoft[name ->„Microsoft“; boss -> bill_gates; revenue(2002) -> 28.370.000.000] • subclasses: company::organization • class-membership: microsoft:company • queries:
Semantic Construction • compositional semantics approach to map NL questions to F-Logic queries • relies on LTAG-style parsing formalism developed in [Muskens 01] • extension to accommodate ontological concepts [Cimiano & Reyle 03]
Who Who owns Microsoft?
Who owns Who owns Microsoft?
Who Microsoft owns Who owns Microsoft?
? Who Microsoft owns Who owns Microsoft?
? Who Microsoft owns Who owns Microsoft?
? Who Who owns Microsoft? owns Microsoft
? Who ei owns Microsoft Who owns Microsoft?
Who owns Microsoft? ? Who ei owns Microsoft
Lexicon Generation (part I) • person[own->company] • use corpus (BNC) • parse it (LoPar) • extract with tgrep • S V O (transitive) • S V PP (intransitive + PP) • S V O PP (transitive + PP) • N PP • N PP PP • find most appropriate synset for each argument w.r.t WordNet [Resnik 97]
Lexicon Generation (part II) person[own -> company] own: transitive: (45.90%) subj: 100001740 obj: 100001740 instransitive + PP: (4.10%) subj: 100001740 PP(by): 100017954 take the one maximizing: repeat the whole process with synonyms of most frequent synset, i.e. have and possess
Lexicon Generation (part III) person[own->company] • own(subj: person, obj: company) Generate elementary trees: • Who owns Microsoft? • Which company does Bill Gates own? • Which company is owned by Bill Gates?
Microsoft company Lexicon Generation (part IV) Microsoft:company
Evaluation • 5 ontologies from the DAML library: • beer • wine • personal information • general information about organizations • university activities • acquire an appropriate subcategorization frame for the binary relations
Conclusion ORAKEL: translating NL questions into logical form • theoretical (parsing) framework • lexicon generation differs from: • AQUALOG (map triples to an ontology) • FrameNet (mapping lexical/semantic representations) • AID (use TFIDF-based similarity) • Schema-based (map words to database columns)
Further Work Further applications: • NL generation from an ontology • Mapping from syntax to ontological structures (MOSES) Further Work: • user feedback • answer formulation • real life evaluation • application to construct the KB
EKAW 2004 Workshop on the Application of Language and Semantic Technologies to support Knowledge Management Submission deadline: 4. July!!! Topics: • Multi-lingual systems, • Information Extraction, • Ontology Learning, • Document Indexing, Retrieval and Browsing, • Approaches to Semantic Annotation, • Smart Browsing, • Semantic Search, • Question Answering, • Enterprise Content Management Organizing Committee: • Philipp Cimiano, AIFB, University of Karlsruhe, Germany. • Fabio Ciravegna, Natural Language Processing Group, University of Sheffield, UK • Enrico Motta, Knowledge Media Institute, The Open University, UK. • Victoria Uren, Knowledge Media Institute, The Open University, UK.