12 |
Universal Dependencies 2.0 – CoNLL 2017 Shared Task Development and Test Data
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Overview of the SPMRL 2013 shared task: cross-framework evaluation of parsing morphologically rich languages
|
|
|
|
In: Seddah, Djamé, Tsarfaty, Reut, Kübler, Sandra, Candito, Marie, Choi, Jinho, Farkas, Richard, Foster, Jennifer orcid:0000-0002-7789-4853 , Goenaga, Iakes, Gojenola, Koldo, Goldberg, Yoav, Green, Spence, Habash, Nizar, Kuhlmann, Marco, Maier, Wolfgang, Nivre, Joakim, Przepiórkowski, Adam, Roth, Ryan, Seeker, Wolfgang, Versley, Yannick, Vincze, Veronika, Wolinski, Marcin, Wróblewska, Alina and Villemonte de la Clérgerie, Eric (2013) Overview of the SPMRL 2013 shared task: cross-framework evaluation of parsing morphologically rich languages. In: Fourth Workshop on Statistical Parsing of Morphologically Rich Languages, 18 Oct 2013, Seattle, WA. (2013)
|
|
BASE
|
|
Show details
|
|
19 |
Overview of the SPMRL 2013 Shared Task: A Cross-Framework Evaluation of Parsing Morphologically Rich Languages
|
|
|
|
In: Proceedings of the Fourth Workshop on Statistical Parsing of Morphologically-Rich Languages ; https://hal.archives-ouvertes.fr/hal-00877096 ; Proceedings of the Fourth Workshop on Statistical Parsing of Morphologically-Rich Languages, Oct 2013, Seattle, Washington, United States. pp.146--182 (2013)
|
|
BASE
|
|
Show details
|
|
20 |
Hard constraints for grammatical function labelling
|
|
|
|
In: Seeker, Wolfgang, Rehbein, Ines, Kuhn, Jonas and van Genabith, Josef orcid:0000-0003-1322-7944 (2010) Hard constraints for grammatical function labelling. In: ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, 11-16 July 2010, Uppsala, Sweden. (2010)
|
|
Abstract:
For languages with (semi-) free word order (such as German), labelling grammatical functions on top of phrase-structural constituent analyses is crucial for making them interpretable. Unfortunately, most statistical classifiers consider only local information for function labelling and fail to capture important restrictions on the distribution of core argument functions such as subject, object etc., namely that there is at most one subject (etc.) per clause. We augment a statistical classifier with an integer linear program imposing hard linguistic constraints on the solution space output by the classifier, capturing global distributional restrictions. We show that this improves labelling quality, in particular for argument grammatical functions, in an intrinsic evaluation, and, importantly, grammar coverage for treebankbased (Lexical-Functional) grammar acquisition and parsing, in an extrinsic evaluation.
|
|
Keyword:
Computational linguistics
|
|
URL: http://doras.dcu.ie/15988/
|
|
BASE
|
|
Hide details
|
|
|
|