• Corpus ID: 4337795

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

@inproceedings{Seddah2013OverviewOT,
  title={Overview of the SPMRL 2013 Shared Task: A Cross-Framework Evaluation of Parsing Morphologically Rich Languages},
  author={Djam{\'e} Seddah and Reut Tsarfaty and Sandra K{\"u}bler and Marie Candito and Jinho D. Choi and Rich{\'a}rd Farkas and Jennifer Foster and Iakes Goenaga and Koldo Gojenola and Yoav Goldberg and Spence Green and Nizar Habash and Marco Kuhlmann and Wolfgang Maier and Joakim Nivre and Adam Przepi{\'o}rkowski and Ryan Roth and Wolfgang Seeker and Yannick Versley and Veronika Vincze and Marcin Woliński and Alina Wr{\'o}blewska and Eric Villemonte de la Clergerie},
  booktitle={SPMRL@EMNLP},
  year={2013}
}
This paper reports on the first shared task on statistical parsing of morphologically rich languages (MRLs). The task features data sets from nine languages, each available both in constituency and dependency annotation. We report on the preparation of the data sets, on the proposed parsing scenarios, and on the evaluation metrics for parsing MRLs given different representation types. We present and analyze parsing results obtained by the task participants, and then provide an analysis and… 
Introducing the SPMRL 2014 Shared Task on Parsing Morphologically-rich Languages
TLDR
This paper provides a short overview of the 2014 SPMRL shared task goals, data sets, and evaluation setup and describes the description of participating systems and the analysis of their results as part of (Seddah et al., 2014).
Parsing Morphologically Rich Languages with (Mostly) Off-The-Shelf Software and Word Vectors
TLDR
It is now possible to achieve high dependency accuracy using existing parsers without the need for intricate multi-parser schemes even if only small amounts of training data are available, and the use of parser scores for selection of morphological lattice paths is discussed.
CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
TLDR
The task and evaluation methodology is defined, how the data sets were prepared, report and analyze the main results, and a brief categorization of the different approaches of the participating systems are provided.
The LIGM-Alpage architecture for the SPMRL 2013 Shared Task: Multiword Expression Analysis and Dependency Parsing
TLDR
This paper describes the LIGM-Alpage system for the SPMRL 2013 Shared Task, and obtains the best results for French, both for overall parsing and for MWE recognition, using a reparsing architecture that combines several parsers, with both pipeline architecture (MWE recognition followed by parsing), and joint architecture (mWE recognition performed by the parser).
Exploiting the Contribution of Morphological Information to Parsing: the BASQUE TEAM system in the SPRML‘2013 Shared Task
TLDR
This paper presents a dependency parsing system, presented as BASQUE TEAM at the SPMRL’2013 Shared Task, based on the analysis of each morphological feature of the languages, using two freely available and state of the art dependency parsers, MaltParser and Mate.
The AI-KU System at the SPMRL 2013 Shared Task : Unsupervised Features for Dependency Parsing
TLDR
The use of the word categories and embeddings induced from raw text as auxiliary features in dependency parsing and a co-occurrence model with these properties to embed words onto a 25dimensional unit sphere are proposed.
Effective Morphological Feature Selection with MaltOptimizer at the SPMRL 2013 Shared Task
TLDR
This paper presents an extension of MaltOptimizer that explores, one by one and in combination, the features that are geared towards morphology, and extracts an in-depth study that shows which features are actually useful for transition-based parsing.
CoNLL-UL: Universal Morphological Lattices for Universal Dependency Parsing
TLDR
The CoNLL universal lattices (CoNLL-UL) format is proposed, a new annotation format for word lattices that represent morphological analyses, and resources that obey this format for a range of typologically different languages are provided.
Preparing Korean Data for the Shared Task on Parsing Morphologically Rich Languages
This document gives a brief description of Korean data prepared for the SPMRL 2013 shared task. A total of 27,363 sentences with 350,090 tokens are used for the shared task. All constituent trees are
Deep Lexical Segmentation and Syntactic Parsing in the Easy-First Dependency Framework
TLDR
A novel representation of token segmentation as trees on tokens, resembling dependency trees is proposed, and two different architectures to combine MWE recognition and dependency parsing in the easy-first framework are presented and evaluated.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 162 REFERENCES
Statistical Parsing of Morphologically Rich Languages (SPMRL) What, How and Whither
TLDR
This paper synthesizes the contributions of researchers working on parsing Arabic, Basque, French, German, Hebrew, Hindi and Korean to point out shared solutions across languages and suggests itself as a source of directions for future investigations.
The CoNLL 2007 Shared Task on Dependency Parsing
TLDR
The tasks of the different tracks are defined and how the data sets were created from existing treebanks for ten languages are described, to characterize the different approaches of the participating systems and report the test results and provide a first analysis of these results.
The LIGM-Alpage architecture for the SPMRL 2013 Shared Task: Multiword Expression Analysis and Dependency Parsing
TLDR
This paper describes the LIGM-Alpage system for the SPMRL 2013 Shared Task, and obtains the best results for French, both for overall parsing and for MWE recognition, using a reparsing architecture that combines several parsers, with both pipeline architecture (MWE recognition followed by parsing), and joint architecture (mWE recognition performed by the parser).
Exploiting the Contribution of Morphological Information to Parsing: the BASQUE TEAM system in the SPRML‘2013 Shared Task
TLDR
This paper presents a dependency parsing system, presented as BASQUE TEAM at the SPMRL’2013 Shared Task, based on the analysis of each morphological feature of the languages, using two freely available and state of the art dependency parsers, MaltParser and Mate.
CoNLL-X Shared Task on Multilingual Dependency Parsing
TLDR
How treebanks for 13 languages were converted into the same dependency format and how parsing performance was measured is described and general conclusions about multi-lingual parsing are drawn.
Single Malt or Blended? A Study in Multilingual Parser Optimization
TLDR
A two-stage optimization of the MaltParser system for the ten languages in the multilingual track of the CoNLL 2007 shared task on dependency parsing results in an ensemble system that combines six different parsing strategies, extrapolating from the optimal parameter settings for each language.
The AI-KU System at the SPMRL 2013 Shared Task : Unsupervised Features for Dependency Parsing
TLDR
The use of the word categories and embeddings induced from raw text as auxiliary features in dependency parsing and a co-occurrence model with these properties to embed words onto a 25dimensional unit sphere are proposed.
Overview of the 2012 Shared Task on Parsing the Web
TLDR
A shared task on parsing web text from the Google Web Treebank to build a single parsing system that is robust to domain changes and can handle noisy text that is commonly encountered on the web is described.
Effective Morphological Feature Selection with MaltOptimizer at the SPMRL 2013 Shared Task
TLDR
This paper presents an extension of MaltOptimizer that explores, one by one and in combination, the features that are geared towards morphology, and extracts an in-depth study that shows which features are actually useful for transition-based parsing.
Knowledge Sources for Constituent Parsing of German, a Morphologically Rich and Less-Configurational Language
TLDR
This work uses a probabilistic context-free grammar treebank grammar that has been adapted to the morphologically rich properties of German by markovization and special features added to its productions to create a reranking parser that is the new state of the art in constituency parsing of the TIGER Treebank.
...
1
2
3
4
5
...