Matches in SemOpenAlex for { <https://semopenalex.org/work/W2099689993> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W2099689993 abstract "In this work, we analyze both acoustic and discourse information for Dialog Act (DA) classification of HCRC MapTask dataset. We extract several different acoustic features and exploit these features in a Hidden Markov Model (HMM) to classify acoustic information. For discourse feature extraction, we propose a novel parts-of-speech (POS) tagging technique that effectively reduces the dimensionality of discourse features manyfold. To classify discourse information, we exploit two classifiers such as a HMM and a Support Vector Machine (SVM) respectively. We further obtain classifier fusion between HMM and SVM to improve discourse classification. Finally, we perform an efficient decision-level classifier fusion for both acoustic and discourse information to classify twelve different DAs in HCRC MapTask data. We obtain accuracy of rate 65.2% (58.06% with cross validation) and 55.4% (51.08% with cross validation) DA classification using acoustic and discourse information respectively. Furthermore, we obtain combined accuracy of 68.6% (61.02% with cross validation) for DA classification. These accuracy rates of DA classification are comparable to previously reported results for the same HCRC MapTask dataset. In terms of average Precision and Recall, we obtain accuracy of 74.89% and 69.83% (without cross validation) respectively. Therefore, we obtain much better precision and recall rate for most of the classified DAs when compared to existing works on the same dataset." @default.
- W2099689993 created "2016-06-24" @default.
- W2099689993 creator A5030773861 @default.
- W2099689993 creator A5081863591 @default.
- W2099689993 date "2008-06-01" @default.
- W2099689993 modified "2023-09-26" @default.
- W2099689993 title "Dialog Act classification using acoustic and discourse information of MapTask Data" @default.
- W2099689993 cites W141482854 @default.
- W2099689993 cites W155915536 @default.
- W2099689993 cites W1588374937 @default.
- W2099689993 cites W188759038 @default.
- W2099689993 cites W1911976934 @default.
- W2099689993 cites W1994458317 @default.
- W2099689993 cites W2077674591 @default.
- W2099689993 cites W2087347434 @default.
- W2099689993 cites W2102169711 @default.
- W2099689993 cites W2102953093 @default.
- W2099689993 cites W2112078429 @default.
- W2099689993 cites W2115720563 @default.
- W2099689993 cites W2119821739 @default.
- W2099689993 cites W2341280305 @default.
- W2099689993 cites W2401527985 @default.
- W2099689993 cites W2585580551 @default.
- W2099689993 doi "https://doi.org/10.1109/ijcnn.2008.4633991" @default.
- W2099689993 hasPublicationYear "2008" @default.
- W2099689993 type Work @default.
- W2099689993 sameAs 2099689993 @default.
- W2099689993 citedByCount "2" @default.
- W2099689993 countsByYear W20996899932018 @default.
- W2099689993 crossrefType "proceedings-article" @default.
- W2099689993 hasAuthorship W2099689993A5030773861 @default.
- W2099689993 hasAuthorship W2099689993A5081863591 @default.
- W2099689993 hasConcept C119857082 @default.
- W2099689993 hasConcept C12267149 @default.
- W2099689993 hasConcept C136764020 @default.
- W2099689993 hasConcept C153180895 @default.
- W2099689993 hasConcept C154945302 @default.
- W2099689993 hasConcept C165696696 @default.
- W2099689993 hasConcept C173853756 @default.
- W2099689993 hasConcept C23224414 @default.
- W2099689993 hasConcept C28490314 @default.
- W2099689993 hasConcept C38652104 @default.
- W2099689993 hasConcept C41008148 @default.
- W2099689993 hasConcept C52622490 @default.
- W2099689993 hasConcept C81669768 @default.
- W2099689993 hasConcept C95623464 @default.
- W2099689993 hasConceptScore W2099689993C119857082 @default.
- W2099689993 hasConceptScore W2099689993C12267149 @default.
- W2099689993 hasConceptScore W2099689993C136764020 @default.
- W2099689993 hasConceptScore W2099689993C153180895 @default.
- W2099689993 hasConceptScore W2099689993C154945302 @default.
- W2099689993 hasConceptScore W2099689993C165696696 @default.
- W2099689993 hasConceptScore W2099689993C173853756 @default.
- W2099689993 hasConceptScore W2099689993C23224414 @default.
- W2099689993 hasConceptScore W2099689993C28490314 @default.
- W2099689993 hasConceptScore W2099689993C38652104 @default.
- W2099689993 hasConceptScore W2099689993C41008148 @default.
- W2099689993 hasConceptScore W2099689993C52622490 @default.
- W2099689993 hasConceptScore W2099689993C81669768 @default.
- W2099689993 hasConceptScore W2099689993C95623464 @default.
- W2099689993 hasLocation W20996899931 @default.
- W2099689993 hasOpenAccess W2099689993 @default.
- W2099689993 hasPrimaryLocation W20996899931 @default.
- W2099689993 hasRelatedWork W2100982643 @default.
- W2099689993 hasRelatedWork W2120008580 @default.
- W2099689993 hasRelatedWork W2126100045 @default.
- W2099689993 hasRelatedWork W2160451891 @default.
- W2099689993 hasRelatedWork W2336974148 @default.
- W2099689993 hasRelatedWork W2367316877 @default.
- W2099689993 hasRelatedWork W2378630083 @default.
- W2099689993 hasRelatedWork W2381773606 @default.
- W2099689993 hasRelatedWork W2187500075 @default.
- W2099689993 hasRelatedWork W2345184372 @default.
- W2099689993 isParatext "false" @default.
- W2099689993 isRetracted "false" @default.
- W2099689993 magId "2099689993" @default.
- W2099689993 workType "article" @default.