Search results

• WMT21 Marian translation model (ca-oc)

  1 resources

  Marian NMT model for Catalan to Occitan translation. Primary CUNI submission for WMT21 Multilingual Low-Resource Translation for Indo-European Languages Shared Task.

  Use "WMT21 Marian translation model (ca-oc)"

• The CLASSLA-StanfordNLP model for morphosyntactic annotation of standard Slovenian 1.2

  3 resources

  This model for morphosyntactic annotation of standard Slovenian was built with the CLASSLA-StanfordNLP tool (https://github.com/clarinsi/classla-stanfordnlp) by training on the ssj500k training corpus (http://hdl.handle.net/11356/1210) and using the CLARIN.SI-embed.sl word embeddings (http://hdl.handle.net/11356/1204). The model produces simultaneously UPOS, FEATS and XPOS (MULTEXT-East) labels. The estimated F1 of the XPOS annotations is ~97.06. The difference to the previous version of the model is that the pre-trained embeddings are limited to 250 thousand entries and adapted to the new code base.

  Use "The CLASSLA-StanfordNLP model for morphosyntactic annotation of standard Slovenian 1.2"

• Malach Center User Interface 1.0

  2 resources

  Source code of the first full and running version for the Malach Center User Interface, does not contain data or metadata fo the digital objects and resources.

  Use "Malach Center User Interface 1.0"

• EVALD 2.0 for Foreigners

  3 resources

  EVALD 2.0 for Foreigners is a software for automatic evaluation of surface coherence (cohesion) in Czech texts written by non-native speakers of Czech.

  Use "EVALD 2.0 for Foreigners"

• Tensor2tensor Translation for Docker

  1 resources

  This submission contains Dockerfile for creating a Docker image with compiled Tensor2tensor backend with compatible (TensorFlow Serving) models available in the Lindat Translation service (https://lindat.mff.cuni.cz/services/transformer/). Additionally, the submission contains a web frontend for simple in-browser access to the dockerized backend service. Tensor2Tensor (https://github.com/tensorflow/tensor2tensor) is a library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

  Use "Tensor2tensor Translation for Docker"

• A lexicographical browser for DjVu

  4 resources

  The program is an indexer and browser for the scans of lexicographical paper slips. The slips are presented in DjVu format and an appropriate relational database stores the information about them. The integration of three approaches: incremental search, binary search and the so-called occasional indexing which consists in refinement of the stored information while searching, offers easy and convenient browsing.

  Use "A lexicographical browser for DjVu"

• CUBBITT Translation Models (en-fr) (v1.0)

  3 resources

  CUBBITT En-Fr translation models, exported via TensorFlow Serving, available in the Lindat translation service (https://lindat.mff.cuni.cz/services/translation/). Models are compatible with Tensor2tensor version 1.6.6. For details about the model training (data, model hyper-parameters), please contact the archive maintainer. Evaluation on newstest2014 (BLEU): en->fr: 38.2 fr->en: 36.7 (Evaluated using multeval: https://github.com/jhclark/multeval)

  Use "CUBBITT Translation Models (en-fr) (v1.0)"

• R crawlers for five Slovenian web media 1.0

  7 resources

  Five web-crawlers written in the R language for retrieving Slovenian texts from the news portals 24ur, Dnevnik, Finance, Rtvslo, and Žurnal24. These portals contain political, business, economic and financial content.

  Use "R crawlers for five Slovenian web media 1.0"

• Integrated Parser

  2 resources

  Integrated parser is an application that combines and normalizes outputs of several parsers for Polish. It is based on ENIAM processing stream extended with Polish Dependency Parser, Świgra and POLFIE. Particular parsers may turned on and off according to the user requirements.

  Use "Integrated Parser"

• Multilabel Error Classifier (Icelandic Error Corpus categories) for Sentences (22.01)

  1 resources

  The Icelandic Error Corpus (IEC) was used to fine tune the Icelandic language model IceBERT for sentence classification. The objective was to train grammatical error detection models that could classify whether a sentence contains a particular error type. The model can mark sentences as including one or more of the following issues: coherence, grammar, orthography, other, style and vocabulary. The overall F1 score is a modest 64%. --- Íslenska villumálheildin (IEC) var notuð til að fínþjálfa íslenska mállíkanið IceBERT fyrir flokkun á setningum. Markmiðið var að þjálfa líkan sem getur greint hvort setning innihaldi ákveðna villutegund. Líkanið getur merkt við setningar með einum eða fleiri mörkum af eftirfarandi: coherence, grammar, orthography, other, style og vocabulary. F1 yfir heildina er 64%.

  Use "Multilabel Error Classifier (Icelandic Error Corpus categories) for Sentences (22.01)"