Matches in SemOpenAlex for { <https://semopenalex.org/work/W85072427> ?p ?o ?g. }
Showing items 1 to 48 of
48
with 100 items per page.
- W85072427 abstract "This paper presents the participation of FIDJI system to the Web Question-Answering evaluation campaign organized by Quaero in 2009. FIDJI is an open-domain question-answering system which combines syntactic information with traditional QA techniques such as named entity recognition and term weighting in order to validate answers through multiple documents. It was originally designed to process ``clean'' document collections. Overall results are significantly lower than in traditional campaigns but results (for French evaluation) are quite good compared to other state-of-the-art systems. They show that a syntax-based strategy, applied on uncleaned Web data, can still obtain good results. Moreover, we obtain much higher scores on ``complex'' questions, i.e. `how' and `why' questions, which are more representative of real user needs. These results show that questioning the Web with advanced linguistic techniques can be done without heavy pre-processing and with results that come near to best systems that use strong resources and large structured indexes." @default.
- W85072427 created "2016-06-24" @default.
- W85072427 creator A5056834851 @default.
- W85072427 creator A5060190356 @default.
- W85072427 date "2010-01-01" @default.
- W85072427 modified "2023-10-14" @default.
- W85072427 title "FIDJI: Web Question-Answering at Quaero 2009" @default.
- W85072427 cites W2069263150 @default.
- W85072427 cites W2187188637 @default.
- W85072427 cites W27887006 @default.
- W85072427 cites W3134663722 @default.
- W85072427 cites W6865571 @default.
- W85072427 cites W72956218 @default.
- W85072427 cites W2187736544 @default.
- W85072427 hasPublicationYear "2010" @default.
- W85072427 type Work @default.
- W85072427 sameAs 85072427 @default.
- W85072427 citedByCount "2" @default.
- W85072427 countsByYear W850724272013 @default.
- W85072427 crossrefType "proceedings-article" @default.
- W85072427 hasAuthorship W85072427A5056834851 @default.
- W85072427 hasAuthorship W85072427A5060190356 @default.
- W85072427 hasConcept C136764020 @default.
- W85072427 hasConcept C23123220 @default.
- W85072427 hasConcept C41008148 @default.
- W85072427 hasConcept C44291984 @default.
- W85072427 hasConceptScore W85072427C136764020 @default.
- W85072427 hasConceptScore W85072427C23123220 @default.
- W85072427 hasConceptScore W85072427C41008148 @default.
- W85072427 hasConceptScore W85072427C44291984 @default.
- W85072427 hasLocation W850724271 @default.
- W85072427 hasLocation W850724272 @default.
- W85072427 hasOpenAccess W85072427 @default.
- W85072427 hasPrimaryLocation W850724271 @default.
- W85072427 hasRelatedWork W1512698090 @default.
- W85072427 hasRelatedWork W15319282 @default.
- W85072427 hasRelatedWork W1602056621 @default.
- W85072427 hasRelatedWork W1602736231 @default.
- W85072427 hasRelatedWork W2118091901 @default.
- W85072427 hasRelatedWork W2135033253 @default.
- W85072427 hasRelatedWork W2138279922 @default.
- W85072427 hasRelatedWork W2366644548 @default.
- W85072427 hasRelatedWork W2373213638 @default.
- W85072427 hasRelatedWork W2766216809 @default.
- W85072427 isParatext "false" @default.
- W85072427 isRetracted "false" @default.
- W85072427 magId "85072427" @default.
- W85072427 workType "article" @default.