FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2155115610> ?p ?o ?g. }

• W2155115610 abstract "This thesis investigates how semantic resources can be deployed to improve the accuracy of an open domain question answering (QA) system. In particular, two types of semantic resources have been utilized to answer factoid questions: (1) Semantic parsing techniques are applied to analyze questions for semantic structures and to find phrases in the knowledge source that match these structures. (2) Ontologies are used to extract terms from questions and corpus sentences and to enrich these terms with semantically similar concepts. These resources have been integrated in the Ephyra QA framework and were compared to previously developed syntactic answer extraction approaches. A semantic extractor for factoid answers was devised that generates semantic representations of the question and phrases in the corpus and extracts answer candidates from phrases that are similar to the question. Different query generation techniques are used to retrieve relevant text passages from the corpus, ranging from simple keyword queries over compound terms expanded with synonyms to specific query strings built from predicate-argument structures. A fuzzy similarity metric compares semantic structures at the level of key terms by measuring their pairwise syntactic and semantic similarities and aggregates these term similarities into an overall similarity score. This mechanism is flexible and robust to parsing errors and it maximizes the recall of the semantic answer extractor. Score normalization and combination techniques allow merging answer candidates found with different semantic and syntactic extraction strategies. Several ontologies are used to extract compound terms from questions and answer sentences and to expand terms with alternative representations. (1) A framework for domain-specific ontologies allows integrating expert knowledge on restricted domains. (2) WordNet is used as an open-domain resource of ontological knowledge. (3) A new approach for automatically learning semantic relation between entities and events in a textual corpus is introduced. Semantic structures are extracted from the corpus with a semantic parser and are subsequently transformed into a semantic network that reveals relations between the entities and events in the corpus. These semantic query generation and answer extraction techniques were assessed on factoid questions from past TREC evaluations using the Web as a large open domain corpus, as well as a local domain-specific document collection. The evaluation results show that the semantic extraction approach has a higher precision than Ephyra’s syntactic answer extractors and that a hybrid approach of semantic and syntactic answer extractors outperforms each individual technique. Furthermore, the query expansion techniques can be combined with existing syntactic extractors to boost their accuracy." @default.
• W2155115610 created "2016-06-24" @default.
• W2155115610 creator A5028227133 @default.
• W2155115610 date "2007-01-01" @default.
• W2155115610 modified "2023-09-27" @default.
• W2155115610 title "Deploying Semantic Resources for Open Domain Question Answering" @default.
• W2155115610 cites W12836875 @default.
• W2155115610 cites W1486774762 @default.
• W2155115610 cites W1492509605 @default.
• W2155115610 cites W1514997941 @default.
• W2155115610 cites W1522989131 @default.
• W2155115610 cites W1531859941 @default.
• W2155115610 cites W1576423642 @default.
• W2155115610 cites W1966878439 @default.
• W2155115610 cites W1988790447 @default.
• W2155115610 cites W2005148043 @default.
• W2155115610 cites W2014333219 @default.
• W2155115610 cites W2025910815 @default.
• W2155115610 cites W2032210760 @default.
• W2155115610 cites W2038721957 @default.
• W2155115610 cites W2056714990 @default.
• W2155115610 cites W2060494110 @default.
• W2155115610 cites W2078396654 @default.
• W2155115610 cites W2083342911 @default.
• W2155115610 cites W2083745421 @default.
• W2155115610 cites W2085806398 @default.
• W2155115610 cites W2091896764 @default.
• W2155115610 cites W2096765155 @default.
• W2155115610 cites W2097410050 @default.
• W2155115610 cites W2098162425 @default.
• W2155115610 cites W2112450612 @default.
• W2155115610 cites W2119325477 @default.
• W2155115610 cites W2119630560 @default.
• W2155115610 cites W2126851059 @default.
• W2155115610 cites W2145073242 @default.
• W2155115610 cites W2152011797 @default.
• W2155115610 cites W2153820555 @default.
• W2155115610 cites W2158890594 @default.
• W2155115610 cites W2611071287 @default.
• W2155115610 cites W2756585732 @default.
• W2155115610 cites W27887006 @default.
• W2155115610 cites W2885050925 @default.
• W2155115610 hasPublicationYear "2007" @default.
• W2155115610 type Work @default.
• W2155115610 sameAs 2155115610 @default.
• W2155115610 citedByCount "3" @default.
• W2155115610 countsByYear W21551156102018 @default.
• W2155115610 crossrefType "journal-article" @default.
• W2155115610 hasAuthorship W2155115610A5028227133 @default.
• W2155115610 hasConcept C130318100 @default.
• W2155115610 hasConcept C140146324 @default.
• W2155115610 hasConcept C154945302 @default.
• W2155115610 hasConcept C186644900 @default.
• W2155115610 hasConcept C199360897 @default.
• W2155115610 hasConcept C204321447 @default.
• W2155115610 hasConcept C23123220 @default.
• W2155115610 hasConcept C2777530160 @default.
• W2155115610 hasConcept C41008148 @default.
• W2155115610 hasConcept C44291984 @default.
• W2155115610 hasConcept C67277372 @default.
• W2155115610 hasConceptScore W2155115610C130318100 @default.
• W2155115610 hasConceptScore W2155115610C140146324 @default.
• W2155115610 hasConceptScore W2155115610C154945302 @default.
• W2155115610 hasConceptScore W2155115610C186644900 @default.
• W2155115610 hasConceptScore W2155115610C199360897 @default.
• W2155115610 hasConceptScore W2155115610C204321447 @default.
• W2155115610 hasConceptScore W2155115610C23123220 @default.
• W2155115610 hasConceptScore W2155115610C2777530160 @default.
• W2155115610 hasConceptScore W2155115610C41008148 @default.
• W2155115610 hasConceptScore W2155115610C44291984 @default.
• W2155115610 hasConceptScore W2155115610C67277372 @default.
• W2155115610 hasLocation W21551156101 @default.
• W2155115610 hasOpenAccess W2155115610 @default.
• W2155115610 hasPrimaryLocation W21551156101 @default.
• W2155115610 hasRelatedWork W1551844433 @default.
• W2155115610 hasRelatedWork W1565175571 @default.
• W2155115610 hasRelatedWork W203104278 @default.
• W2155115610 hasRelatedWork W2097410050 @default.
• W2155115610 hasRelatedWork W2133976672 @default.
• W2155115610 hasRelatedWork W2153937728 @default.
• W2155115610 hasRelatedWork W230203381 @default.
• W2155115610 hasRelatedWork W2348509553 @default.
• W2155115610 hasRelatedWork W2373453601 @default.
• W2155115610 hasRelatedWork W2385202360 @default.
• W2155115610 hasRelatedWork W2387095251 @default.
• W2155115610 hasRelatedWork W2396482335 @default.
• W2155115610 hasRelatedWork W2481480215 @default.
• W2155115610 hasRelatedWork W2546892695 @default.
• W2155115610 hasRelatedWork W2564481580 @default.
• W2155115610 hasRelatedWork W2611660938 @default.
• W2155115610 hasRelatedWork W263400564 @default.
• W2155115610 hasRelatedWork W3014064593 @default.
• W2155115610 hasRelatedWork W748083353 @default.
• W2155115610 hasRelatedWork W2928446862 @default.
• W2155115610 isParatext "false" @default.
• W2155115610 isRetracted "false" @default.
• W2155115610 magId "2155115610" @default.
• W2155115610 workType "article" @default.