CoNLL 2017 Shared Task - UDPipe Baseline Models and Supplementary Materials

  Authors

Straka, Milan

  Item identifier

http://hdl.handle.net/11234/1-1990

 Project URL

http://ufal.mff.cuni.cz/udpipe

 Date issued

2017-03-15

 Type

languageDescription, text

 Language(s)

Multiple languages

 Description

Baseline UDPipe models for CoNLL 2017 Shared Task in UD Parsing, and supplementary material. The models require UDPipe version at least 1.1 and are evaluated using the official evaluation script. The models are trained on a slightly different split of the official UD 2.0 CoNLL 2017 training data, so called baselinemodel split, in order to allow comparison of models even during the shared task. This baselinemodel split of UD 2.0 CoNLL 2017 training data is available for download. Furthermore, we also provide UD 2.0 CoNLL 2017 training data with automatically predicted morphology. We utilize the baseline models on development data and perform 10-fold jack-knifing (each fold is predicted with a model trained on the rest of the folds) on the training data. Finally, we supply all required data and hyperparameter values needed to replicate the baseline models.

 Publisher

Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)

 Acknowledgement

Ministerstvo školství, mládeže a tělovýchovy České republiky

Project code: LM2015071

Project name: LINDAT/CLARIN: Institut pro analýzu, zpracování a distribuci lingvistických dat

 

Univerzita Karlova (mimo GAUK)

Project code: SVV 260 333

Project name: Specifický vysokoškolský výzkum

 

Grantová agentura České republiky

Project code: 15-10472S

Project name: Morphologically and Syntactically Annotated Corpora of Many Languages

 Subject(s)

CoNLL 2017 tokenizer POS tagger lemmatization tagger parser dependency parser morphology treebank

 Collection(s)

LINDAT / CLARIAH-CZ Data & Tools

Show full item record