Rodyti trumpą aprašą

dc.contributor.authorKolesau, Aliaksei
dc.contributor.authorŠešok, Dmitrij
dc.contributor.authorRybokas, Mindaugas
dc.date.accessioned2023-09-18T16:42:24Z
dc.date.available2023-09-18T16:42:24Z
dc.date.issued2018
dc.identifier.issn1453-8245
dc.identifier.urihttps://etalpykla.vilniustech.lt/handle/123456789/116188
dc.description.abstractThis article presents a simple method to perform part-of-speech (POS) tagging with feedforward neural networks applied to learnable character embeddings. The motivation of the research is based on the fact that for some languages a human can find out the part of speech for a word just by its spelling even without knowing the meaning of the word (see C.Fries’s example “woggles ugged diggles”). One of the goals was to achieve high accuracy tagging without using semantic information (e.g. without word embeddings). This allows performing tagging for out of vocabulary words. Also, the dependency of the performance from context size was studied. The plausibility of the method was proved by building a POStagger with the accuracy comparable to state-of-the-art results.eng
dc.formatPDF
dc.format.extentp. 446-459
dc.format.mediumtekstas / txt
dc.language.isoeng
dc.relation.isreferencedbyScopus
dc.relation.isreferencedbyScience Citation Index Expanded (Web of Science)
dc.source.urihttp://www.romjist.ro/full-texts/paper612.pdf
dc.titleA character-based part-of-speech tagger with feedforward neural networks
dc.typeStraipsnis Web of Science DB / Article in Web of Science DB
dcterms.references26
dc.type.pubtypeS1 - Straipsnis Web of Science DB / Web of Science DB article
dc.contributor.institutionVilniaus Gedimino technikos universitetas
dc.contributor.facultyFundamentinių mokslų fakultetas / Faculty of Fundamental Sciences
dc.subject.researchfieldT 007 - Informatikos inžinerija / Informatics engineering
dc.subject.vgtuprioritizedfieldsIK0303 - Dirbtinio intelekto ir sprendimų priėmimo sistemos / Artificial intelligence and decision support systems
dc.subject.ltspecializationsL106 - Transportas, logistika ir informacinės ir ryšių technologijos (IRT) / Transport, logistic and information and communication technologies
dc.subject.enPOS tagging
dc.subject.encharacter embeddings
dc.subject.enfeedforward neural networks
dcterms.sourcetitleRomanian journal of information science and technology
dc.description.issueno. 4
dc.description.volumevol. 21
dc.publisher.nameEditura Academiei Romane/Publishing House of the Romanian Academy
dc.publisher.cityBucharest
dc.identifier.doi000455901500009
dc.identifier.elaba33187751


Šio įrašo failai

FailaiDydisFormatasPeržiūra

Su šiuo įrašu susijusių failų nėra.

Šis įrašas yra šioje (-se) kolekcijoje (-ose)

Rodyti trumpą aprašą