CLARIN Tool Portal

Toposław 2 (2016-05-31)

3 resources

Toposław 2 is an editor of multi-world unit inflection lexicons.

Use "Toposław 2 (2016-05-31)"

Liner2.6 NER NKJP model The package contains a pre-trained Liner2 (https://github.com/CLARIN-PL/Liner2) model for recognition named entities according to NKJP guidelines. The model was trained on the NKJP corpus (http://nkjp.pl/) and evaluated in the PolEval 2018 Task 2 (http://poleval.pl/tasks/). The model won third place with the following results: Exact — 0.778, Overlap — 0.818, Final — 0.810. References: * NKJP corpus in TEI format — http://clip.ipipan.waw.pl/NationalCorpusOfPolish?action=AttachFile&do=view&target=NKJP-PodkorpusMilionowy-1.2.tar.gz * PolEval 2018 Task 2 evaluation corpus — http://mozart.ipipan.waw.pl/~axw/poleval2018/

Use "Liner2.6 model NER NKJP"

Paralela corpus and search engine

3 resources

Paralela is as an open-ended, opportunistic parallel corpus of Polish-English and English-Polish translations. It currently contains 262 million words in 10,877,000 translation segments. The Paralela online search engine supports the SlopeQ query syntax for bilingual Polish-English corpus queries for the full dataset. Both the full texts and query results can be accessed and exported through the online application at http://paralela.clarin-pl.eu.

Use "Paralela corpus and search engine"

PELCRA for National Corpus of Polish Search Engine 2

2 resources

The PELCRA for NKJP search engine 2 provides access to the full National Corpus of Polish dataset (over 1.5 billion word tokens). In addition to linguistically motivated corpus queries, it supports a number of data exploration and visualisation features. Most of the functionality of the search engine is available through a REST web service. Access to the API is available upon request.

Use "PELCRA for National Corpus of Polish Search Engine 2"

XLM-RoBERTa-LARGE events relation recognition

1 resources

A set of basic language tools for the Polish language. Z4.2a Improving the quality of recognition of relations between events using Transformer-type deep networks.

Use "XLM-RoBERTa-LARGE events relation recognition"

WiKNN Text Classifier

2 resources

WiKNN is an online text classifier service for Polish and English texts. It supports hierarchical labelled classification of user-submitted texts with Wikipedia categories. WiKNN is available through a web-based interface (http://pelcra.clarin-pl.eu/tools/classifier/) and as a REST service with interactive documentation available at http://clarin.pelcra.pl/apidocs/wiknn.

Use "WiKNN Text Classifier"

DG-POLFIE: POLFIE and Malt-based syntactic parser

1 resources

DG-POLFIE is a prototypical parser that tries to merge parse fragments generated by POLFIE using Polish Dependency Parser DG-POLFIE aims to improve the coverage of the POLFIE parser (i.e. the percentage of sentences with at least one analysis). In order to increase the number of Polish sentences and constructions that could be parsed with the POLFIE-based parser, DG-POLFIE defines some rules that use depenency structure to build full parse from the FRAGMENTS provided by POLFIE.

Use "DG-POLFIE: POLFIE and Malt-based syntactic parser"