Konferensartikel

Universal Dependencies for Greek

Prokopis Prokopidis
Institute for Language and Speech Processing, Athena Research Center, Athens, Greece

Haris Papageorgiou
Institute for Language and Speech Processing, Athena Research Center, Athens, Greece

Ladda ner artikel

Ingår i: Proceedings of the NoDaLiDa 2017 Workshop on Universal Dependencies, 22 May, Gothenburg Sweden

Linköping Electronic Conference Proceedings 135:13, s. 102-106

NEALT Proceedings Series 31:13, p. 102-106

Visa mer +

Publicerad: 2017-05-29

ISBN: 978-91-7685-501-0

ISSN: 1650-3686 (tryckt), 1650-3740 (online)

Abstract

This paper describes work towards the harmonization of the Greek Dependency Treebank with the Universal Dependencies v2 standard, and the extension of the treebank with enhanced dependencies. Experiments with the latest version of the UD_Greek resource have led to 88.94/87.66 LAS on gold/automatic POS, morphological features and lemmas.

Nyckelord

Inga nyckelord är tillgängliga

Referenser

Anagnostopoulou, D., E. Desipri, P. Labropoulou, E. Mantzari, and M. Gavrilidou (2000). Lexis - Lexicographical Infrastructure: Systematising the Data. In: Computational Lexicography (COMLEX 2000).

Böhmová, A., J. Hajic, E. Hajicová, and B. Hladká (2003). The Prague Dependency Treebank: A  Three-Level Annotation Scenario. In: Treebanks: Building and Using Parsed Corpora. Kluwer.

Bohnet, B. (2010). Very High Accuracy and Fast Dependency Parsing is Not a Contradiction. In: Proceedings of the 23rd International Conference on Computational Linguistics, pp. 89–97.

Bojanowski, P., E. Grave, A. Joulin, and T. Mikolov (2016). Enriching Word Vectors with Subword Information. In: CoRR abs/1607.04606.

Holton, D., P. Mackridge, and I. Philippaki-Warburton (1997). Greek: A comprehensive grammar of the modern language. London and New York: Routledge.

Kiperwasser, E. and Y. Goldberg (2016). Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations. In: Transactions of the Association for Computational Linguistics 4, pp. 313–327.

Nivre, J., M.-C. de Marneffe, F. Ginter, Y. Goldberg, J. Hajic, C. D. Manning, R. McDonald, S. Petrov, S. Pyysalo, N. Silveira, R. Tsarfaty, and D. Zeman (2016). Universal Dependencies v1: A Multilingual Treebank Collection. In: Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016).

Nivre, J. and J. Nilsson (2005). Pseudo-Projective Dependency Parsing. In: Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL), pp. 99–106.

Papageorgiou, H., P. Prokopidis, V. Giouli, and S. Piperidis (2000). A Unified POS Tagging Architecture and its Application to Greek. In: Proceedings of the 2nd Language Resources and Evaluation Conference. European Language Resources Association, pp. 1455–1462.

Prokopidis, P., E. Desypri, M. Koutsombogera, H. Papageorgiou, and S. Piperidis (2005). Theoretical and practical issues in the construction of a Greek Dependency Treebank. In: Proceedings of the Fourth Workshop on Treebanks and Linguistic Theories.

Prokopidis, P. and H. Papageorgiou (2014). Experiments for Dependency Parsing of Greek. In: Proceedings of the First Joint Workshop on Statistical Parsing of Morphologically Rich Languages and Syntactic Analysis of Non-Canonical Languages, pp. 90–96.

Schuster, S. and C. D. Manning (2016). Enhanced English Universal Dependencies: An Improved Representation for Natural Language Understanding Tasks. In: Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016).

Straka, M., J. Hajic, and J. Straková (2016). UDPipe: Trainable Pipeline for Processing CoNLLU Files Performing Tokenization, Morphological Analysis, POS Tagging and Parsing. In: Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016).

Zeman, D., O. Dušek, D. Marecek, M. Popel, L. Ramasamy, J. Štepánek, Z. Žabokrtský, and J. Hajic (2014). HamleDT: Harmonized Multilanguage dependency treebank. In: Language Resources and Evaluation 48.4, pp. 601–637.

Citeringar i Crossref