14 Hits in 5.1 sec

Overview of the SPMRL 2013 Shared Task: A Cross-Framework Evaluation of Parsing Morphologically Rich Languages

Djamé Seddah, Reut Tsarfaty, Sandra Kübler, Marie Candito, Jinho D. Choi, Richárd Farkas, Jennifer Foster, Iakes Goenaga, Koldo Gojenola Galletebeitia, Yoav Goldberg, Spence Green, Nizar Habash (+11 others)
2013 Workshop on Statistical Parsing of Morphologically Rich Languages  
This paper reports on the first shared task on statistical parsing of morphologically rich languages (MRLs).  ...  We present and analyze parsing results obtained by the task participants, and then provide an analysis and comparison of the parsers across languages and frameworks, reported for gold input as well as  ...  Without all of you, this shared task would not have been possible.  ... 
dblp:conf/acl-spmrl/SeddahTKCCFFGGG13 fatcat:5ngltl7jr5hu5o72goudyy4tuq

(Re)ranking Meets Morphosyntax: State-of-the-art Results from the SPMRL 2013 Shared Task

Anders Björkelund, Özlem Çetinoglu, Richárd Farkas, Thomas Mueller, Wolfgang Seeker
2013 Workshop on Statistical Parsing of Morphologically Rich Languages  
This paper describes the IMS-SZEGED-CIS contribution to the SPMRL 2013 Shared Task. We participate in both the constituency and dependency tracks, and achieve state-of-theart for all languages.  ...  For both tracks we make significant improvements through high quality preprocessing and (re)ranking on top of strong baselines. Our system came out first for both tracks.  ...  Acknowledgments Richárd Farkas is funded by the European Union and the European Social Fund through the project (grant no.: T ÁMOP-4.2.2.C-11/1/KONV-  ... 
dblp:conf/acl-spmrl/BjorkelundCFMS13 fatcat:vs2qiiujvbavfel2i3qzkgyjey

CoNLL-SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection in 52 Languages [article]

Ryan Cotterell, Christo Kirov, John Sylak-Glassman, Géraldine Walther, Ekaterina Vylomova, Patrick Xia, Manaal Faruqui, Sandra Kübler, David Yarowsky, Jason Eisner, Mans Hulden
2017 arXiv   pre-print
The CoNLL-SIGMORPHON 2017 shared task on supervised morphological generation required systems to be trained and tested in each of 52 typologically diverse languages.  ...  Following the success of neural sequence-to-sequence models in the SIGMORPHON 2016 shared task, all but one of the submissions included a neural component.  ...  Acknowledgements The first author would like to acknowledge the support of an NDSEG fellowship. Google provided support for the shared task in the form of an award.  ... 
arXiv:1706.09031v2 fatcat:qt6qyq6kqban5hol5txt7ssft4

Telugu dependency parsing using different statistical parsers

B. Venkata Seshu Kumari, Ramisetty Rajeshwara Rao
2017 Journal of King Saud University: Computer and Information Sciences  
We report our results on test data of Telugu dependency treebank provided in the ICON 2010 tools contest on Indian languages dependency parsing.  ...  We also provide a detailed analysis of the performance of all the parsers on major dependency labels.  ...  Different approaches are being explored in the Statistical Parsing of Morphologically Rich Languages (SPMRL) workshops (Seddah et al., 2010; Seddah et al., 2011; Apidianaki et al., 2012; Goldberg et al  ... 
doi:10.1016/j.jksuci.2014.12.006 fatcat:rg3isskzorbihb46fckkcrc3my

Multiword Expression Processing: A Survey

Mathieu Constant, Gülşen Eryiğit, Johanna Monti, Lonneke van der Plas, Carlos Ramisch, Michael Rosner, Amalia Todirascu
2017 Computational Linguistics  
It offers a shared understanding of what is meant by "MWE processing," distinguishing the subtasks of MWE discovery and identification.  ...  We propose a conceptual framework within which challenges and research contributions can be positioned.  ...  This work has been partially funded by the French National Research Agency (ANR) through the PARSEME-FR project (ANR-14-CERA-0001) and by a TUBITAK 1001 grant (no: 112E276).  ... 
doi:10.1162/coli_a_00302 fatcat:rjrfyfbfpfblfbtwpbdqnpgsiu

Treebanking user-generated content: a UD based overview of guidelines, corpora and unified recommendations

Manuela Sanguinetti, Cristina Bosco, Lauren Cassidy, Özlem Çetinoğlu, Alessandra Teresa Cignarella, Teresa Lynn, Ines Rehbein, Josef Ruppenhofer, Djamé Seddah, Amir Zeldes
2022 Language Resources and Evaluation  
The overarching goal of this article is to provide a common framework for researchers interested in developing similar resources in UD, thus promoting cross-linguistic consistency, which is a principle  ...  1) to provide a condensed, though comprehensive, overview of such treebanks—based on available literature—along with their main features and a comparative analysis of their annotation criteria, and (2)  ...  To view a copy of this licence, visit  ... 
doi:10.1007/s10579-022-09581-9 fatcat:qq37mznqojclrlrx72o3tyesxq

Task-based parser output combination : workflow and infrastructure [article]

Kerstin Eckart, Universität Stuttgart, Universität Stuttgart
Moreover, the evaluation of the combined complete analyses does not reflect the reliability achieved in the analysis of the specific aspects needed to resolve a given task.  ...  This dissertation introduces the method of task-based parser output combination as a device to enhance the reliability of automatically generated syntactic information for further processing tasks.  ...  I wish to thank all the people inside and outside of the IMS, sharing and discussing the PhD experience with me, Gertrud, Carolin, Michael, Marie, Benjamin, to name just a few.  ... 
doi:10.18419/opus-9853 fatcat:uqcylmhbqbgz5atv3q3egf4zma

Multilingual Chart-based Constituency Parse Extraction from Pre-trained Language Models

Taeuk Kim, Bowen Li, Sang-goo Lee
2021 Findings of the Association for Computational Linguistics: EMNLP 2021   unpublished
de la Clergerie. 2013. Overview of the SPMRL 2013 shared task: A cross-framework evaluation of parsing morphologically rich languages.  ...  In Proceed- ings of the Fourth Workshop on Statistical Parsing of Morphologically-Rich Languages.  ... 
doi:10.18653/v1/2021.findings-emnlp.41 fatcat:pftm7vkyi5bz3hm4ptuvdgi4dq

Ensemble dependency parsing across languages : methodological perspectives [article]

Agnieszka Faleńska, Universität Stuttgart
This dissertation focuses on one of the essential Natural Language Processing tasks - dependency parsing.  ...  Parsing is usually one of the processing steps that helps downstream NLP tasks by resolving some of the syntactic ambiguities occurring in sentences.  ...  We perform experiments on the treebanks from the SPMRL 2014 shared task on parsing morphologically-rich languages (Seddah et al., 2014 Preprocessing.  ... 
doi:10.18419/opus-11605 fatcat:hk4m3zcgy5eqhbw22mxlyrb45m

hr500k – A Reference Training Corpus of Croatian

Nikola Ljubešić, Željko Agić, Filip Klubicka, Vuk Batanović, Tomaž Erjavec
We also give a description of the rather turbulent history of the resource and give insights into the topic and genre distribution in the corpus.  ...  We present each annotation layer via basic label statistics and describe the final encoding of the resource in CoNLL and TEI formats.  ...  Parsing Croatian and Serbian by using Croatian dependency treebanks. In Proceedings of the Fourth Workshop on Statistical Parsing of Morphologically Rich Languages (SPMRL 2013).  ... 
doi:10.21427/0pjb-f168 fatcat:spx5qs3kn5givhjv3uis7viuby

Modeling the interface between morphology and syntax in data-driven dependency parsing [article]

Wolfgang Seeker, Universität Stuttgart, Universität Stuttgart
These languages are commonly subsumed under the term morphologically rich languages. Parsing is the automatic process for predicting the grammatical structure of a sentence.  ...  This dissertation is about parsing and specifically about parsing languages with a rich morphology, which encode grammatical information in the form of words.  ...  We use the pre-disambiguated lattices provided by the SPMRL 2014 Shared Task as the baseline for Hebrew. Seddah et al. (2013: 159) give a description on how these lattices are produced.  ... 
doi:10.18419/opus-8949 fatcat:vsmsey2wfnfzhgjg67th5wx3v4

Online learning of latent linguistic structure with approximate search [article]

Anders Björkelund, Universität Stuttgart, Universität Stuttgart
This framework supports latent structures and is agnostic of the particular language processing task.  ...  The advantage of this modularization is that it permits comparisons and reuse across tasks in a common framework. The framework we devise is based on the structured perceptron for learning.  ...  In Notes of the SPMRL 2014 Shared Task on Parsing Morphologically-Rich Languages, Dublin, Ireland UD Shared Task: CRFs and Perceptrons Meet Neural Networks.  ... 
doi:10.18419/opus-10232 fatcat:bncmvn7iyzckvf5qioxefbqrby

EM-Training for Weighted Aligned Hypergraph Bimorphisms

Frank Drewes, Kilian Gebhardt, Heiko Vogler
2016 Proceedings of the SIGFSM Workshop on Statistical NLP and Weighted Automata   unpublished
In particular in morphologically rich languages there is a large number of word forms that occur only seldom in spoken and written language.  ...  A conversion of TiGer has, for instance, been used in the CoNLL-X shared task on dependency parsing (Buchholz and Marsi 2006) .  ...  Its configurations consist of a stack with an additional pointer, a buffer, and, at least for dependency parsing, a set of arcs. 14 The buffer is initialized with the input sentence.  ... 
doi:10.18653/v1/w16-2407 fatcat:b7nu3kfrevavzlzi3ovz4oe3ym

Étudiants du Master Linguistique, spécialité LASTIC de l'Université d'Or-léans Comité de Programme de TALN Comité de Relecture de TALN 2017 7 et INRIA Béatrice Daille, Laboratoire d'Informatique Nantes Atlantique (LINA)

Hyun Kang, Hélène Couderc, Laetitia Delay, Siqi Fan, Lorraine Gaspard, Mélanie Lefeuvre, Sara Masaud, Stéphanie Nogueira, Camille Pertin, Cathy Querineau, Céline Vaschalde, Jidong Xie (+24 others)
de l'Unesco et située à 125 km au sud de Paris.  ...  Le premier jour, lundi, est consacré à quatre ateliers thématiques : « DEFT Fouille de texte » consacré cette année à l'analyse d'opinion et langage figuratif dans des messages postés sur Twitter ; la  ...  Acknowledgments This work was supported by the CRC 991 "The Structure of Representations in Language, Cognition, and Science" funded by the German Research Foundation (DFG).  ...