Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Şaziye Betül Özateş"'
Publikováno v:
IEEE Access, Vol 10, Pp 93867-93886 (2022)
Fully data-driven, deep learning-based models are usually designed as language-independent and have been shown to be successful for many natural language processing tasks. However, when the studied language is not high-resource and the amount of trai
Externí odkaz:
https://doaj.org/article/9030f909c82f49689d09074bb058bc74
Autor:
Şaziye Betül Özateş, Özlem Çetinoğlu
Publikováno v:
Proceedings of the Fifth Workshop on Computational Approaches to Linguistic Code-Switching.
Morphological tagging of code-switching (CS) data becomes more challenging especially when language pairs composing the CS data have different morphological representations. In this paper, we explore a number of ways of implementing a language-aware
Resources for Turkish Dependency Parsing: Introducing the BOUN Treebank and the BoAT Annotation Tool
Autor:
Utku Türk, Furkan Atmaca, Arzucan Özgür, Gözde Berk, Seyyit Talha Bedir, Abdullatif Köksal, Balkız Öztürk Başaran, Şaziye Betül Özateş, Tunga Güngör
In this paper, we introduce the resources that we developed for Turkish dependency parsing, which include a novel manually annotated treebank (BOUN Treebank), along with the guidelines we adopted, and a new annotation tool (BoAT). The manual annotati
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b812262a18ea4ee1c9e1e06043dab94c
Autor:
Furkan Atmaca, Şaziye Betül Özateş, Arzucan Özgür, Balkız Öztürk Başaran, Utku Türk, Tunga Güngör
Publikováno v:
Proceedings of the Third Workshop on Universal Dependencies (UDW, SyntaxFest 2019).
Autor:
Şaziye Betül Özateş, Balkız Öztürk Başaran, Arzucan Özgür, Furkan Atmaca, Utku Türk, Abdullatif Köksal, Tunga Güngör
Publikováno v:
Scopus-Elsevier
LAW@ACL
LAW@ACL
In this paper, we present the current version of two different treebanks, the re-annotation of the Turkish PUD Treebank and the first annotation of the Turkish National Corpus Universal Dependency (henceforth TNC-UD). The annotation of both treebanks
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::63441a3a57d8cbf1310c3a800fe657d1
https://aperta.ulakbim.gov.tr/record/74453
https://aperta.ulakbim.gov.tr/record/74453
Publikováno v:
CoNLL Shared Task (2)
We propose two word representation models for agglutinative languages that better capture the similarities between words which have similar tasks in sentences. Our models highlight the morphological features in words and embed morphological informati