Matches in SemOpenAlex for { <https://semopenalex.org/work/W941608337> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W941608337 abstract "This paper presents the first experiments on identifying implicit discourse relations (i.e., relations lacking an overt discourse connective) in French. Given the little amount of annotated data for this task, our system resorts to additional data automatically labeled using unambiguous connectives, a method introduced by (Marcu and Echihabi, 2002). We first show that a system trained solely on these artificial data does not generalize well to natural implicit examples, thus echoing the conclusion made by (Sporleder and Lascarides, 2008) for English. We then explain these initial results by analyzing the different types of distribution difference between natural and artificial implicit data. This finally leads us to propose a number of very simple methods, all inspired from work on domain adaptation, for combining the two types of data. Through various experiments on the French ANNODIS corpus, we show that our best system achieves an accuracy of 41.7%, corresponding to a 4.4% significant gain over a system solely trained on manually labeled data." @default.
- W941608337 created "2016-06-24" @default.
- W941608337 creator A5044698676 @default.
- W941608337 creator A5058670843 @default.
- W941608337 date "2014-08-23" @default.
- W941608337 modified "2023-10-13" @default.
- W941608337 title "Combining Natural and Artificial Examples to Improve Implicit Discourse Relation Identification" @default.
- W941608337 cites W102059219 @default.
- W941608337 cites W1518867723 @default.
- W941608337 cites W1541881462 @default.
- W941608337 cites W1563792215 @default.
- W941608337 cites W1574440611 @default.
- W941608337 cites W1617650991 @default.
- W941608337 cites W194033037 @default.
- W941608337 cites W1973682096 @default.
- W941608337 cites W2028138594 @default.
- W941608337 cites W2040960947 @default.
- W941608337 cites W2044599851 @default.
- W941608337 cites W2083778102 @default.
- W941608337 cites W2099153428 @default.
- W941608337 cites W2109462987 @default.
- W941608337 cites W2120262106 @default.
- W941608337 cites W2120354757 @default.
- W941608337 cites W2120708938 @default.
- W941608337 cites W2131861279 @default.
- W941608337 cites W2134899753 @default.
- W941608337 cites W2140127231 @default.
- W941608337 cites W2141007997 @default.
- W941608337 cites W2152197045 @default.
- W941608337 cites W2153370481 @default.
- W941608337 cites W2165887782 @default.
- W941608337 cites W2166957049 @default.
- W941608337 cites W2170496269 @default.
- W941608337 cites W2250597058 @default.
- W941608337 cites W2251211118 @default.
- W941608337 cites W2252182164 @default.
- W941608337 cites W2441124914 @default.
- W941608337 cites W2798615787 @default.
- W941608337 cites W29849901 @default.
- W941608337 cites W3141851185 @default.
- W941608337 cites W3146885639 @default.
- W941608337 cites W71968012 @default.
- W941608337 hasPublicationYear "2014" @default.
- W941608337 type Work @default.
- W941608337 sameAs 941608337 @default.
- W941608337 citedByCount "19" @default.
- W941608337 countsByYear W9416083372015 @default.
- W941608337 countsByYear W9416083372016 @default.
- W941608337 countsByYear W9416083372017 @default.
- W941608337 countsByYear W9416083372018 @default.
- W941608337 countsByYear W9416083372019 @default.
- W941608337 countsByYear W9416083372020 @default.
- W941608337 countsByYear W9416083372021 @default.
- W941608337 crossrefType "proceedings-article" @default.
- W941608337 hasAuthorship W941608337A5044698676 @default.
- W941608337 hasAuthorship W941608337A5058670843 @default.
- W941608337 hasBestOaLocation W9416083371 @default.
- W941608337 hasConcept C116834253 @default.
- W941608337 hasConcept C124101348 @default.
- W941608337 hasConcept C154945302 @default.
- W941608337 hasConcept C166957645 @default.
- W941608337 hasConcept C204321447 @default.
- W941608337 hasConcept C25343380 @default.
- W941608337 hasConcept C2776608160 @default.
- W941608337 hasConcept C41008148 @default.
- W941608337 hasConcept C59822182 @default.
- W941608337 hasConcept C86803240 @default.
- W941608337 hasConcept C95457728 @default.
- W941608337 hasConceptScore W941608337C116834253 @default.
- W941608337 hasConceptScore W941608337C124101348 @default.
- W941608337 hasConceptScore W941608337C154945302 @default.
- W941608337 hasConceptScore W941608337C166957645 @default.
- W941608337 hasConceptScore W941608337C204321447 @default.
- W941608337 hasConceptScore W941608337C25343380 @default.
- W941608337 hasConceptScore W941608337C2776608160 @default.
- W941608337 hasConceptScore W941608337C41008148 @default.
- W941608337 hasConceptScore W941608337C59822182 @default.
- W941608337 hasConceptScore W941608337C86803240 @default.
- W941608337 hasConceptScore W941608337C95457728 @default.
- W941608337 hasLocation W9416083371 @default.
- W941608337 hasLocation W9416083372 @default.
- W941608337 hasOpenAccess W941608337 @default.
- W941608337 hasPrimaryLocation W9416083371 @default.
- W941608337 hasRelatedWork W2157140558 @default.
- W941608337 hasRelatedWork W2323648130 @default.
- W941608337 hasRelatedWork W2357797405 @default.
- W941608337 hasRelatedWork W2366623913 @default.
- W941608337 hasRelatedWork W2374905595 @default.
- W941608337 hasRelatedWork W2378782423 @default.
- W941608337 hasRelatedWork W2388988621 @default.
- W941608337 hasRelatedWork W3192589309 @default.
- W941608337 hasRelatedWork W4233308809 @default.
- W941608337 hasRelatedWork W4234874385 @default.
- W941608337 isParatext "false" @default.
- W941608337 isRetracted "false" @default.
- W941608337 magId "941608337" @default.
- W941608337 workType "article" @default.