{"id":2974,"identifier":"data/ERDJDI","persistentUrl":"https://doi.org/10.11588/data/ERDJDI","protocol":"doi","authority":"10.11588","publisher":"heiDATA","publicationDate":"2019-10-07","storageIdentifier":"file://10.11588/data/ERDJDI","datasetVersion":{"id":426,"datasetId":2974,"datasetPersistentId":"doi:10.11588/data/ERDJDI","storageIdentifier":"file://10.11588/data/ERDJDI","versionNumber":1,"versionMinorNumber":0,"versionState":"RELEASED","productionDate":"2016","lastUpdateTime":"2019-10-07T10:24:19Z","releaseTime":"2019-10-07T10:24:19Z","createTime":"2019-07-08T09:21:04Z","publicationDate":"2019-10-07","citationDate":"2019-10-07","termsOfUse":"Licensed under General Public License v3 (GPL v3). ","fileAccessRequest":false,"metadataBlocks":{"citation":{"displayName":"Citation Metadata","name":"citation","fields":[{"typeName":"title","multiple":false,"typeClass":"primitive","value":"Multilingual Modal Sense Classification using a Convolutional Neural Network [Source Code]"},{"typeName":"alternativeURL","multiple":false,"typeClass":"primitive","value":"https://github.com/amarasovic/modal-sense-classifcation"},{"typeName":"author","multiple":true,"typeClass":"compound","value":[{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Marasović, Ana"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"Department of Computational Linguistics, Heidelberg University, Germany"}}]},{"typeName":"datasetContact","multiple":true,"typeClass":"compound","value":[{"datasetContactName":{"typeName":"datasetContactName","multiple":false,"typeClass":"primitive","value":"Marasović, Ana"},"datasetContactAffiliation":{"typeName":"datasetContactAffiliation","multiple":false,"typeClass":"primitive","value":"Department of Computational Linguistics, Heidelberg University, Germany"},"datasetContactEmail":{"typeName":"datasetContactEmail","multiple":false,"typeClass":"primitive","value":"anam@allenai.org"}}]},{"typeName":"dsDescription","multiple":true,"typeClass":"compound","value":[{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"
Abstract
\r\nModal sense classification (MSC) is aspecial WSD task that depends on themeaning of the proposition in the modal’s scope. We explore a CNN architecture for classifying modal sense in English and German. We show that CNNs are superior to manually designed feature-based classifiers and a standard NN classifier. We analyze the feature maps learned by the CNN and identify known and previously unattested linguistic features. We bench-mark the CNN on a standard WSD task,where it compares favorably to models using sense-disambiguated target vectors.
\r\n(Marasović and Frank, 2016)
"}}]},{"typeName":"subject","multiple":true,"typeClass":"controlledVocabulary","value":["Arts and Humanities","Computer and Information Science"]},{"typeName":"keyword","multiple":true,"typeClass":"compound","value":[{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"Modal sense classification (MSC)"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"Word Sense Disambiguation"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"modal verb"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"word embedding"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"semantic feature"}}]},{"typeName":"topicClassification","multiple":true,"typeClass":"compound","value":[{"topicClassValue":{"typeName":"topicClassValue","multiple":false,"typeClass":"primitive","value":"semantic modeling"}}]},{"typeName":"publication","multiple":true,"typeClass":"compound","value":[{"publicationCitation":{"typeName":"publicationCitation","multiple":false,"typeClass":"primitive","value":"Marasović, A. and Frank, A. (2016). Multilingual modal sense classification using a convolutional neural network. In Proceedings of the 1st Workshop on Representation Learning for NLP, pages 111–120, August 11, 2016, Berlin, Germany. Association for Computational Linguistics.
"},"publicationIDType":{"typeName":"publicationIDType","multiple":false,"typeClass":"controlledVocabulary","value":"doi"},"publicationIDNumber":{"typeName":"publicationIDNumber","multiple":false,"typeClass":"primitive","value":"10.18653/v1/W16-1613"},"publicationURL":{"typeName":"publicationURL","multiple":false,"typeClass":"primitive","value":"https://doi.org/10.18653/v1/W16-1613"}}]},{"typeName":"productionDate","multiple":false,"typeClass":"primitive","value":"2016"},{"typeName":"productionPlace","multiple":true,"typeClass":"primitive","value":["Heidelberg University"]},{"typeName":"kindOfData","multiple":true,"typeClass":"primitive","value":["program source code, python scripts"]},{"typeName":"relatedMaterial","multiple":true,"typeClass":"primitive","value":["TensorFlow
\r\nVersion: r0.12
\r\nLink to the https://github.com/tensorflow/tensorflow/tree/r0.12
\r\nLicense: Apache License 2.0
"]},{"typeName":"relatedDatasets","multiple":true,"typeClass":"primitive","value":["The MSC Data Set:
Link to the dataset: https://doi.org/10.11588/data/JEESIQ (heiDATA)