Filters








161 Hits in 1.3 sec

The Alpino Dependency Treebank [chapter]

Leonoor van der Beek, Gosse Bouma, Rob Malouf, Gertjan van Noord
Computational Linguistics in the Netherlands 2001  
In this paper we present the Alpino Dependency Treebank and the tools that we have developed to facilitate the annotation process.  ...  At this moment, the Alpino Dependency Treebank consists of about 6,000 sentences of newspaper text that are annotated with dependency trees.  ...  The treebank currently contains over 6,000 sentences. 6 Much effort will be put in extending the treebank to at least the complete cdbl newspaper part of the Eindhoven corpus, which contains 7,150 sentences  ... 
doi:10.1163/9789004334038_003 fatcat:ey7zmswdxnaebmcgubrullw5by

Dependency Treebanks: Methods, Annotation Schemes and Tools [article]

Tuomo Kakkonen
2006 arXiv   pre-print
In this paper, current dependencybased treebanks are introduced and analyzed.  ...  The methods used for building the resources, the annotation schemes applied, and the tools used (such as POS taggers, parsers and annotation software) are discussed.  ...  Acknowledgments The research reported in this work has been supported by the European Union under a Marie Curie Host Fellowship for Early Stage Researchers Training at MUL-TILINGUA, Bergen, Norway and  ... 
arXiv:cs/0610124v1 fatcat:ndrnaldljzgrzimthqc4ryjyku

Self-Trained Bilexical Preferences to Improve Disambiguation Accuracy [chapter]

Gertjan van Noord
2010 Text, Speech and Language Technology  
as: Alpino -treebank_dep_features Treebank/cdb/4.xml will output the dependency features found in the XML file specified on the command line.  ...  The standard version of Alpino that we use here as baseline system is trained on the 145,000 word Alpino treebank, which contains dependency structures for the cdbl (newspaper) part of the Eindhoven corpus  ...  An alternative approach that is explored here, is the use of the Alpino parser itself. Alpino is capable of extracting dependency triples of a given XML-file containing a dependency relation.  ... 
doi:10.1007/978-90-481-9352-3_11 fatcat:ezlyyoq525fvvkcfnqyxco325m

GrETEL. A Tool for Example-Based Treebank Mining [chapter]

2017 CLARIN in the Low Countries  
A major asset of GrETEL is that it enables non-technical users to consult treebanks in a user-friendly way, which is also in line with the main CLARIN goal of applying the results of speech and language  ...  It provides online access to the data, allowing users to query a treebank using either an example sentence or an XPath expression in order to look for similar constructions.  ...  Acknowledgements The work on GrETEL was carried out in the framework of the following projects:  ... 
doi:10.5334/bbi.22 fatcat:3kcm77r3hvee5icmayzrcjpwli

Page 83 of Computational Linguistics Vol. 34, Issue 1 [page]

2008 Computational Linguistics  
Traditionally, deep grammars are hand-crafted (cf. the ALVEY Natural Language Tools [Briscoe et al. 1987], the Core Language Engine [Alshawi and Pulman 1992], the Alpino Dutch dependency parser [Bouma,  ...  van Noord, and Malouf 2000], the Xerox Lin- guistic Environment [Butt et al. 2002], the RASP dependency parser [Carroll and Briscoe 2002] and the LinGO English Resource Grammar [Flickinger 2000; Baldwin  ... 

Computational linguistics

2016 2016 Third International Conference on Information Retrieval and Knowledge Management (CAMP)  
As one of the design goals of the Alpino-treebank was to produce output compatible with CGN, it seems that the annotation guidelines for either Alpino or CGN need to be reconsidered.  ...  in there have I totally no desire for I have no desire for that at all The Alpino-treebank of written Dutch, 1 on the other hand, has opted for the V+PP analysis.  ... 
doi:10.1109/infrkm.2016.7806324 fatcat:yyirdddomjcpzjtz7wolprd2sy

Computational Linguistics [chapter]

2013 Encyclopedia of Systems Biology  
As one of the design goals of the Alpino-treebank was to produce output compatible with CGN, it seems that the annotation guidelines for either Alpino or CGN need to be reconsidered.  ...  in there have I totally no desire for I have no desire for that at all The Alpino-treebank of written Dutch, 1 on the other hand, has opted for the V+PP analysis.  ... 
doi:10.1007/978-1-4419-9863-7_100251 fatcat:hekuzcopn5etzcswwjvuyxfi2i

Computational Linguistics [chapter]

2012 Intelligence Science  
As one of the design goals of the Alpino-treebank was to produce output compatible with CGN, it seems that the annotation guidelines for either Alpino or CGN need to be reconsidered.  ...  in there have I totally no desire for I have no desire for that at all The Alpino-treebank of written Dutch, 1 on the other hand, has opted for the V+PP analysis.  ... 
doi:10.1142/9789814360784_0008 fatcat:26ed6ulbxjew3jruddyy3npmsq

DepAnn - An Annotation Tool for Dependency Treebanks [article]

Tuomo Kakkonen
2006 arXiv   pre-print
DepAnn is an interactive annotation tool for dependency treebanks, providing both graphical and text-based annotation interfaces. The tool is aimed for semi-automatic creation of treebanks.  ...  A novel feature of the tool is that it enables the user to view outputs from several parsers as the basis for creating the final tree to be saved to the treebank.  ...  The work was partly conducted while the author was working at the Human Language Technology Group at the Council for Scientific and Industrial Research (CSIR), Pretoria, South Africa and at the Faculty  ... 
arXiv:cs/0610116v1 fatcat:re5mlf5lgndq3bdco7on3up77m

Computational linguistics and grammar engineering [article]

Emily M. Bender, Guy Emerson
2021 Zenodo  
We discuss the relevance of HPSG for computational linguistics, and the relevance of computational linguistics for HPSG, including: the theoretical and computational infrastructure required to carry out  ...  Alpino uses a statistical model trained on a dependency treebank, and in fact the same statistical model can be used in both parsing and generation (de Kok et al. 2011).  ...  The Alpino parser was similarly used to construct the Lassy Treebanks of written Dutch (van Noord et al. 2013) .  ... 
doi:10.5281/zenodo.5599867 fatcat:qfrfqb5fnngdtbbqhhm3dkmmua

Going Dutch: Creating SimpleNLG-NL

Ruud de Jong, Mariët Theune
2018 Proceedings of the 11th International Conference on Natural Language Generation  
It describes a novel method for determining and testing the grammatical constructions to be implemented, using target sentences sampled from a treebank.  ...  This paper presents SimpleNLG-NL, an adaptation of the SimpleNLG surface realisation engine for the Dutch language.  ...  Acknowledgements This research was carried out partially within the POSTHCARD project, funded by the European AAL programme (aal-call-2017-045).  ... 
doi:10.18653/v1/w18-6508 dblp:conf/inlg/JongT18 fatcat:dsotszabdvhp7hizw4qj2ukmpa

Incremental sentence production inhibits clausal coordinate ellipsis: A treebank study into Dutch and German

Karin Harbusch
2011 Dialogue and Discourse  
We present a treebank study into CCE in written and spoken Dutch and German which confirms this tendency.  ...  We argue that the detailed data pattern cannot be accounted for in terms of audience design, and propose an explanation based on the assumption that during spontaneous speaking-but not during writing-,  ...  Acknowledgement I would like to express my deep gratitude to Gerard Kempen, who co-authored several related articles on the present topic.  ... 
doi:10.5087/dad.2011.112 fatcat:4q3fs74bdzcxhatubysgt4q55e

BasiScript

Agnes Tellings, Nelleke Oostdijk, Iris Monster, Franc Grootjen, Antal van den Bosch
2018 International Journal of Corpus Linguistics  
Each word token in the corpus is annotated with the correct orthographical form, the associated lemma and the part of speech.  ...  The most frequent polysemous words have been annotated for word meaning, while all words in the lexicon that was derived from the BasiScript corpus have been annotated for corpus and subcorpora frequency  ...  Thanks also to the anonymous reviewers for valuable suggestions. We are indebted to Gertjan van Noord and his co-workers for their invaluable work on the Alpino parser.  ... 
doi:10.1075/ijcl.17086.tel fatcat:wcvmqx5rb5gvfdkpegep34w3ou

The DCU-EPFL Enhanced Dependency Parser at the IWPT 2021 Shared Task [article]

James Barry, Alireza Mohammadshahi, Joachim Wagner, Jennifer Foster, James Henderson
2021 arXiv   pre-print
We describe the DCU-EPFL submission to the IWPT 2021 Shared Task on Parsing into Enhanced Universal Dependencies.  ...  The task involves parsing Enhanced UD graphs, which are an extension of the basic dependency trees designed to be more facilitative towards representing semantic structure.  ...  We would like to thank the shared task organizers as well as the anonymous reviewers for their helpful feedback.  ... 
arXiv:2107.01982v1 fatcat:gsim4yb6rvfahpck6uhxfnlvki

Køpsala: Transition-Based Graph Parsing via Efficient Training and Effective Encoding [article]

Daniel Hershcovich, Miryam de Lhoneux, Artur Kulmizev, Elham Pejhan, Joakim Nivre
2020 arXiv   pre-print
We present Køpsala, the Copenhagen-Uppsala system for the Enhanced Universal Dependencies Shared Task at IWPT 2020.  ...  Our parser demonstrates that a unified pipeline is effective for both Meaning Representation Parsing and Enhanced Universal Dependencies.  ...  Acknowledgments We thank the anonymous reviewers for their helpful comments. ML is funded by a Google Focused Research Award.  ... 
arXiv:2005.12094v2 fatcat:jouxxzlghzh3tdslg4dxvgyina
« Previous Showing results 1 — 15 out of 161 results