By : Vanessa López, Enrico Motta Knowledge Media Institute. Open University Ontology-driven question answering in: AQUALog 9 th International Conference on Applications of Natural Language to Information Systems NLDB’04 {v.lopez,
Ontology-driven Question Answering in AquaLog Vanessa López NLDB’04 Index Motivation: NL front-end for the Semantic Web AquaLog approach System Architecture Examples Evaluation/ Discussion Future Lines/ Conclusions
Ontology-driven Question Answering in AquaLog Vanessa López NLDB’04 The future web : -knowledge to be managed in an automatic way The Semantic Web Vision Semantics through: - Set of representation languages: rdf,… - Structures for knowledge: ontologies ASSUMPTION: Ontology-based semantic markup will become widely available Engineering Semantics on the Web ?
Ontology-driven Question Answering in AquaLog Vanessa López NLDB’04 Question-Answering - Novel, sophisticated Question Answering using Semantic Mark-up - Semantic Mark-up queried directly Similar scenario - asking NL queries to databases (semantic mark-up viewed as a knowledge base) So… Ontology portable
Ontology-driven Question Answering in AquaLog Vanessa López NLDB’04 For instance..
Ontology-driven Question Answering in AquaLog Vanessa López NLDB’04 Example!!: What are the projects of enrico motta?
Ontology-driven Question Answering in AquaLog Vanessa López NLDB’04 AquaLog: Approach NL SENTENCE INPUT LINGUISTIC & QUERY CLASSIFICATION RELATION SIMILARITY SERVICE INFERENCE ENGINE QUERY TRIPLES ONTOLOGY COMPATIBLE TRIPLES ANSWER Intermediate triples: + features
Ontology-driven Question Answering in AquaLog Vanessa López NLDB’04 2 main subtasks: Intermediate representation from the input query Map the intermediate representation to the kb Ontologíes Knowledge Bases ? PLUG-INS AQUALOG AquaLog: Approach Linguistic Component: Relation Similarity Service:
Ontology-driven Question Answering in AquaLog Vanessa López NLDB’04 Linguistic Component USER’S SESSION QUERY INTERFACE LINGUISTIC COMPONENT GATE LIBRARIES NL QUERY TRIPLES NL QUERY TERMS VERBS FEATURES TOKENS NOUNS PREPS WH-S TRIPLE(s) RELATIONS JAPE TERMS RELATIONS WH-TERMS QUERY-PATTERN-CLASSIFICATION
Ontology-driven Question Answering in AquaLog Vanessa López NLDB’04 Linguistic Component WH-GENERIC TERM: projects? – involved - semantic web person/organization? - managed (passive) - motta WH-UNKNOWN TERM: value?– job title - motta WH-UNKNOWN RELATION : DESCRIPTION: AFFIRMATIVE-NEGATIVE: COMBINATION OF BASIC QUERIES: value?– web address -- peter person/organization? – has interest – semantic web
Ontology-driven Question Answering in AquaLog Vanessa López NLDB’04 Ontologies LINGUISTIC TRIPLE RSS USER MECHANISM(S) Relation Similarity Service
Ontology-driven Question Answering in AquaLog Vanessa López NLDB’04 The relation similarity service ? Relations/concepts similarities Translated queryOntological structures THE PROBLEM dynamic secretary(person, KMI) works-in-unit (secretary, knowledge-media-institute) Who is the secretary in Kmi? RSS Research institute
Ontology-driven Question Answering in AquaLog Vanessa López NLDB’04
Ontology-driven Question Answering in AquaLog Vanessa López NLDB’04 CATEGORY: WH-UNKNOWN TERM QUERY TRIPLE: VALUE? – PROJECTS – JOHN DOMINGUE USER’S FEEDBACK REQUIRED!! PROJECT? – ? - JOHN DOMINGUE What are the projects of john domingue
Ontology-driven Question Answering in AquaLog Vanessa López NLDB’04 ONTO TRIPLE: PROJECTS – HAS-PROJECT-MEMBER (OR) HAS-PROJECT-LEADER- JOHN-DOMINGUE ANSWER: LIST OF PROJECTS
Ontology-driven Question Answering in AquaLog Vanessa López NLDB’04
Ontology-driven Question Answering in AquaLog Vanessa López NLDB’04 CATERGORY: WH-GENERIC TERM QUERY TRIPLE: RESEARCH AREAS – COVERED -AKT ONTO TRIPLE: RESEARCH-AREA – ADDRESSES-GENERIC- AREA-OF-INTEREST – AKT SOLUTION: LIST OF RESEARCH AREAS What are the research areas covered by the akt project ?
Ontology-driven Question Answering in AquaLog Vanessa López NLDB’04
Ontology-driven Question Answering in AquaLog Vanessa López NLDB’04
Ontology-driven Question Answering in AquaLog Vanessa López NLDB’04 AquaLog: Architecture USER’S SESSION QUERY INTERFACE ANSWERING PROCESSING INTERFACE Gate libraries Configuration files LINGUISTIC COMPONENT String pattern libraries Configuration files HelpRSS-IE modules Interpreter WordNet thesaurus libraries Ontologíes Knowledge Bases RELATION SIMILARITY SERVICE TRIPLES QUERY ‘Raw’ Answer Ontology-compliant query Answer User’s feedback Post-process Semantic modules
Ontology-driven Question Answering in AquaLog Vanessa López NLDB’04 Evaluation Initial study: - Satisfy the users expectations about the range of questions? - Possible extensions to the ontology and linguistic components? - 70 questions: no linguistic constraints % of the total were handled correctly Aktive-reference ontology ? LINGUISTIC FAILURE DATA MODEL FAILURE RSS FAILURE CONCEPTUAL FAILURE SERVICE FAILURE NLP -> TRIPLE 69% of errors NL too complicate for triples 0% of errors Query TRIPLE Onto TRIPLE 7.6% of errors Ontology does no cover query 10.2% of errors requires ranking and similarity services 20.5% of errors
Ontology-driven Question Answering in AquaLog Vanessa López NLDB’04 AquaLog version 2 -Improved linguistic coverage: - which researchers wrote publications related to social aspects? -Implementing services -Similarity services: is there a project similar to akt? -Ranking services: what are the most successful projects? NEW VERSION TO HANDLE 87% OF THE FAILURES
Ontology-driven Question Answering in AquaLog Vanessa López NLDB’04 Current work: Example Are there any projects about ontologies sponsored by eprsc? CLAUSE CATEGORY: WH-GENERIC-1TERM-CLAUSE QUERY TRIPLE: SPONSORED (PROJECTS, ONTOLOGY, EPRSC) CATEGORY: WH-UNKNOWN-REL ONTO TRIPLE: ADDRESSES-GENERIC-AREA-OF- INTEREST (PROJECT?, ONTOLOGIES) CATEGORY: WH-GENERIC-TERM ONTO TRIPLE: FUNDING SOURCE (PROJECT?, ONTOLOGIES) SOLUTION(WH-GENERIC-1TERM-CLAUSE): COMBINATION OF LISTS
Ontology-driven Question Answering in AquaLog Vanessa López NLDB’04 Which projects are headed by researchers in akt? CLAUSEIS A CLASS! CATEGORY: WH--3TERM QUERY TRIPLE: HEADED (PROJECTS, RESEARCHERS, AKT) CATEGORY: WH-3TERM ONTO TRIPLE: HAS-PROJECT-MEMBER OR LEADER (PROJECT?, RESEARCHER) CATEGORY: WH-UNKNOWN-REL ONTO TRIPLE: HAS-PROJECT-MEMBER OR LEADER (RESEARCHERS, AKT) SOLUTION(WH-3-TERM – CLAUSE TO THE 2 TERM): GET THE FIRST LIST FOR THE CLAUSE AND GET A LIST FOR EACH OF THE ELEMENTS IN THE LIST Current work: Example
Ontology-driven Question Answering in AquaLog Vanessa López NLDB’04 Conclusion Novel RSS Service: combination of pattern matching, lexicon & reasoning about the ontology (taxonomy, relationships). Term (Triple): instance/class Relation (Triple): relation/class (not necessarily known) Linguistic Component: GATE (Sheffield university). Very flexible through the use of patterns: currently around 26 linguistic patterns. String algorithms find matching in the ontology for any of the triple terms. Based on combination of string distance metrics for name matching tasks (open source: Carnegie Melon University – Pittsburgh) Portable little configuration effort Portability across ontologies have to be evaluated
Ontology-driven Question Answering in AquaLog Vanessa López NLDB’04 End Thanks for your attention