English-Turkish parallel treebank with morphological annotations and its use in tree-based SMT

Basit Öğe Kaydı
dc.authorid0000-0001-7754-2033
dc.authorid0000-0001-5838-4615
dc.authorid0000-0002-8448-9987
dc.contributor.authorGörgün, Onuren_US
dc.contributor.authorYıldız, Olcay Taneren_US
dc.contributor.authorSolak, Ercanen_US
dc.contributor.authorEhsani, Raziehen_US
dc.date.accessioned2016-08-11T17:35:14Z
dc.date.available2016-08-11T17:35:14Z
dc.date.issued2016
dc.departmentIşık Üniversitesi, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümüen_US
dc.departmentIşık University, Faculty of Engineering, Department of Computer Engineeringen_US
dc.description.abstractIn this paper, we report our tree based statistical translation study from English to Turkish. We describe our data generation process and report the initial results of tree-based translation under a simple model. For corpus construction, we used the Penn Treebank in the English side. We manually translated about 5K trees from English to Turkish under grammar constraints with adaptations to accommodate the agglutinative nature of Turkish morphology. We used a permutation model for subtrees together with a word to word mapping. We report BLEU scores under simple choices of inference algorithms.en_US
dc.description.versionPublisher's Versionen_US
dc.identifier.citationGörgün, O., Yıldız, O. T., Solak, E. & Ehsani, R. (2016). English-turkish parallel treebank with morphological annotations and its use in tree-based SMT. Paper presented at the Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods (ICPRAM 2016), 510-516. doi:10.5220/0005653905100516en_US
dc.identifier.doi10.5220/0005653905100516
dc.identifier.endpage516
dc.identifier.isbn9789897581731
dc.identifier.scopus2-s2.0-84969940458
dc.identifier.scopusqualityN/A
dc.identifier.startpage510
dc.identifier.urihttps://hdl.handle.net/11729/1112
dc.identifier.urihttp://dx.doi.org/10.5220/0005653905100516
dc.indekslendigikaynakScopusen_US
dc.institutionauthorYıldız, Olcay Taneren_US
dc.institutionauthorSolak, Ercanen_US
dc.institutionauthorEhsani, Raziehen_US
dc.institutionauthorid0000-0001-5838-4615
dc.institutionauthorid0000-0002-8448-9987
dc.language.isoenen_US
dc.peerreviewedYesen_US
dc.publicationstatusPublisheden_US
dc.publisherSciTePressen_US
dc.relation.ispartofProceedings of the 5th International Conference on Pattern Recognition Applications and Methods (ICPRAM 2016)en_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectMachine translationen_US
dc.subjectTree-based translationen_US
dc.subjectInference enginesen_US
dc.subjectPattern recognitionen_US
dc.subjectCorpus constructionen_US
dc.subjectData generationen_US
dc.subjectInference algorithmen_US
dc.subjectMachine translationsen_US
dc.subjectSimple modelingen_US
dc.subjectStatistical translationen_US
dc.subjectTree-baseden_US
dc.subjectTree-based smten_US
dc.subjectTrees (mathematics)en_US
dc.titleEnglish-Turkish parallel treebank with morphological annotations and its use in tree-based SMTen_US
dc.typeConference Objecten_US
dspace.entity.typePublication

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim
İsim:
1112.pdf
Boyut:
170.57 KB
Biçim:
Adobe Portable Document Format
Açıklama:
Publisher's Version
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.71 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Bildiri Koleksiyonu | Bilgisayar Mühendisliği Bölümü
Scopus İndeksli Yayınlar Koleksiyonu