Matches in SemOpenAlex for { <https://semopenalex.org/work/W2002382481> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2002382481 abstract "This paper describes a methodology for semi-supervised learning of dialogue acts using the similarity between sentences. We suppose that the dialogue sentences with the same dialogue act are more similar in terms of semantic and syntactic information. However, previous work on sentence similarity mainly modeled a sentence as bag-of-words and then compared different groups of words using corpus-based or knowledge-based measurements of word semantic similarity. Novelly, we present a vector-space sentence representation, composed of word embeddings, that is, the related word distributed representations, and these word embeddings are organised in a sentence syntactic structure. Given the vectors of the dialogue sentences, a distance measurement can be well-defined to compute the similarity between them. Finally, a seeded k-means clustering algorithm is implemented to classify the dialogue sentences into several categories corresponding to particular dialogue acts. This constitutes the semi-supervised nature of the approach, which aims to ameliorate the reliance of the availability of annotated corpora. Experiments with Switchboard Dialog Act corpus show that classification accuracy is improved by 14%, compared to the state-of-art methods based on Support Vector Machine." @default.
- W2002382481 created "2016-06-24" @default.
- W2002382481 creator A5004605359 @default.
- W2002382481 creator A5011972821 @default.
- W2002382481 creator A5057117256 @default.
- W2002382481 creator A5068149448 @default.
- W2002382481 date "2014-07-01" @default.
- W2002382481 modified "2023-10-18" @default.
- W2002382481 title "Semi-supervised learning of dialogue acts using sentence similarity based on word embeddings" @default.
- W2002382481 cites W1508927691 @default.
- W2002382481 cites W192515608 @default.
- W2002382481 cites W2022470916 @default.
- W2002382481 cites W2042096436 @default.
- W2002382481 cites W2119183593 @default.
- W2002382481 cites W2121184547 @default.
- W2002382481 cites W2128970689 @default.
- W2002382481 cites W2129577276 @default.
- W2002382481 cites W2142120379 @default.
- W2002382481 cites W2401527985 @default.
- W2002382481 cites W4252434862 @default.
- W2002382481 doi "https://doi.org/10.1109/icalip.2014.7009921" @default.
- W2002382481 hasPublicationYear "2014" @default.
- W2002382481 type Work @default.
- W2002382481 sameAs 2002382481 @default.
- W2002382481 citedByCount "5" @default.
- W2002382481 countsByYear W20023824812016 @default.
- W2002382481 countsByYear W20023824812018 @default.
- W2002382481 countsByYear W20023824812021 @default.
- W2002382481 countsByYear W20023824812023 @default.
- W2002382481 crossrefType "proceedings-article" @default.
- W2002382481 hasAuthorship W2002382481A5004605359 @default.
- W2002382481 hasAuthorship W2002382481A5011972821 @default.
- W2002382481 hasAuthorship W2002382481A5057117256 @default.
- W2002382481 hasAuthorship W2002382481A5068149448 @default.
- W2002382481 hasConcept C103278499 @default.
- W2002382481 hasConcept C111919701 @default.
- W2002382481 hasConcept C115961682 @default.
- W2002382481 hasConcept C130318100 @default.
- W2002382481 hasConcept C13336665 @default.
- W2002382481 hasConcept C138885662 @default.
- W2002382481 hasConcept C154945302 @default.
- W2002382481 hasConcept C17744445 @default.
- W2002382481 hasConcept C199539241 @default.
- W2002382481 hasConcept C204321447 @default.
- W2002382481 hasConcept C2524010 @default.
- W2002382481 hasConcept C2776359362 @default.
- W2002382481 hasConcept C2777530160 @default.
- W2002382481 hasConcept C2778572836 @default.
- W2002382481 hasConcept C33923547 @default.
- W2002382481 hasConcept C41008148 @default.
- W2002382481 hasConcept C41895202 @default.
- W2002382481 hasConcept C73555534 @default.
- W2002382481 hasConcept C90805587 @default.
- W2002382481 hasConcept C94625758 @default.
- W2002382481 hasConceptScore W2002382481C103278499 @default.
- W2002382481 hasConceptScore W2002382481C111919701 @default.
- W2002382481 hasConceptScore W2002382481C115961682 @default.
- W2002382481 hasConceptScore W2002382481C130318100 @default.
- W2002382481 hasConceptScore W2002382481C13336665 @default.
- W2002382481 hasConceptScore W2002382481C138885662 @default.
- W2002382481 hasConceptScore W2002382481C154945302 @default.
- W2002382481 hasConceptScore W2002382481C17744445 @default.
- W2002382481 hasConceptScore W2002382481C199539241 @default.
- W2002382481 hasConceptScore W2002382481C204321447 @default.
- W2002382481 hasConceptScore W2002382481C2524010 @default.
- W2002382481 hasConceptScore W2002382481C2776359362 @default.
- W2002382481 hasConceptScore W2002382481C2777530160 @default.
- W2002382481 hasConceptScore W2002382481C2778572836 @default.
- W2002382481 hasConceptScore W2002382481C33923547 @default.
- W2002382481 hasConceptScore W2002382481C41008148 @default.
- W2002382481 hasConceptScore W2002382481C41895202 @default.
- W2002382481 hasConceptScore W2002382481C73555534 @default.
- W2002382481 hasConceptScore W2002382481C90805587 @default.
- W2002382481 hasConceptScore W2002382481C94625758 @default.
- W2002382481 hasLocation W20023824811 @default.
- W2002382481 hasOpenAccess W2002382481 @default.
- W2002382481 hasPrimaryLocation W20023824811 @default.
- W2002382481 hasRelatedWork W2002382481 @default.
- W2002382481 hasRelatedWork W2116838603 @default.
- W2002382481 hasRelatedWork W2151108588 @default.
- W2002382481 hasRelatedWork W2252122760 @default.
- W2002382481 hasRelatedWork W2361793880 @default.
- W2002382481 hasRelatedWork W2463465470 @default.
- W2002382481 hasRelatedWork W2741632991 @default.
- W2002382481 hasRelatedWork W2766760871 @default.
- W2002382481 hasRelatedWork W3078371441 @default.
- W2002382481 hasRelatedWork W2305519505 @default.
- W2002382481 isParatext "false" @default.
- W2002382481 isRetracted "false" @default.
- W2002382481 magId "2002382481" @default.
- W2002382481 workType "article" @default.