Graph-based Syntactic Word Embeddings

dc.contributorAalto-yliopistofi
dc.contributorAalto Universityen
dc.contributor.authorAl-Ghezi, Ragheben_US
dc.contributor.authorKurimo, Mikkoen_US
dc.contributor.departmentSpeech Recognitionen_US
dc.contributor.departmentDept Signal Process and Acousten_US
dc.date.accessioned2021-02-09T09:07:05Z
dc.date.available2021-02-09T09:07:05Z
dc.date.issued2020-12-30en_US
dc.description.abstractWe propose a simple and efficient framework to learn syntactic embeddings based on information derived from constituency parse trees. Using biased random walk methods, our embeddings not only encode syntactic information about words, but they also capture contextual information. We also propose a method to train the embeddings on multiple constituency parse trees to ensure the encoding of global syntactic representation. Quantitative evaluation of the embeddings shows competitive performance on POS tagging task when compared to other types of embeddings, and qualitative evaluation reveals interesting facts about the syntactic typology learned by these embeddings.en
dc.description.versionPeer revieweden
dc.format.extent7
dc.format.extent72–78
dc.format.mimetypeapplication/pdfen_US
dc.identifier.citationAl-Ghezi , R & Kurimo , M 2020 , Graph-based Syntactic Word Embeddings . in Proceedings of the Graph-based Methods for Natural Language Processing (TextGraphs) . Association for Computational Linguistics , pp. 72–78 , Workshop on Graph-Based Methods for Natural Language Processing , Barcelona , Spain , 13/12/2020 . < https://www.aclweb.org/anthology/2020.textgraphs-1.8/ >en
dc.identifier.isbn978-1-952148-42-2
dc.identifier.otherPURE UUID: a76488f9-9d1e-43df-9a93-2438af027c8den_US
dc.identifier.otherPURE ITEMURL: https://research.aalto.fi/en/publications/a76488f9-9d1e-43df-9a93-2438af027c8den_US
dc.identifier.otherPURE LINK: https://www.aclweb.org/anthology/2020.textgraphs-1.8/en_US
dc.identifier.otherPURE FILEURL: https://research.aalto.fi/files/55769418/Graph_based_Syntactic_Word_Embeddings.pdfen_US
dc.identifier.urihttps://aaltodoc.aalto.fi/handle/123456789/102662
dc.identifier.urnURN:NBN:fi:aalto-202102091962
dc.language.isoenen
dc.relation.ispartofWorkshop on Graph-Based Methods for Natural Language Processingen
dc.relation.ispartofseriesProceedings of the Graph-based Methods for Natural Language Processing (TextGraphs)en
dc.rightsopenAccessen
dc.titleGraph-based Syntactic Word Embeddingsen
dc.typeConference article in proceedingsfi
Files