Search results

• Czech image captioning, machine translation, and sentiment analysis (Neural Monkey models)

  7 resources

  This submission contains trained end-to-end models for the Neural Monkey toolkit for Czech and English, solving three NLP tasks: machine translation, image captioning, and sentiment analysis. The models are trained on standard datasets and achieve state-of-the-art or near state-of-the-art performance in the tasks. The models are described in the accompanying paper. The same models can also be invoked via the online demo: https://ufal.mff.cuni.cz/grants/lsd There are several separate ZIP archives here, each containing one model solving one of the tasks for one language. To use a model, you first need to install Neural Monkey: https://github.com/ufal/neuralmonkey To ensure correct functioning of the model, please use the exact version of Neural Monkey specified by the commit hash stored in the 'git_commit' file in the model directory. Each model directory contains a 'run.ini' Neural Monkey configuration file, to be used to run the model. See the Neural Monkey documentation to learn how to do that (you may need to update some paths to correspond to your filesystem organization). The 'experiment.ini' file, which was used to train the model, is also included. Then there are files containing the model itself, files containing the input and output vocabularies, etc. For the sentiment analyzers, you should tokenize your input data using the Moses tokenizer: https://pypi.org/project/mosestokenizer/ For the machine translation, you do not need to tokenize the data, as this is done by the model. For image captioning, you need to: - download a trained ResNet: http://download.tensorflow.org/models/resnet_v2_50_2017_04_14.tar.gz - clone the git repository with TensorFlow models: https://github.com/tensorflow/models - preprocess the input images with the Neural Monkey 'scripts/imagenet_features.py' script (https://github.com/ufal/neuralmonkey/blob/master/scripts/imagenet_features.py) -- you need to specify the path to ResNet and to the TensorFlow models to this script Feel free to contact the authors of this submission in case you run into problems!

  Use "Czech image captioning, machine translation, and sentiment analysis (Neural Monkey models)"

• KER - Keyword Extractor

  3 resources

  KER is a keyword extractor that was designed for scanned texts in Czech and English. It is based on the standard tf-idf algorithm with the idf tables trained on texts from Wikipedia. To deal with the data sparsity, texts are preprocessed by Morphodita: morphological dictionary and tagger.

  Use "KER - Keyword Extractor"

• SlopeQ for BNC Search Engine

  2 resources

  The SlopeQ for BNC Search Engine provides access to the British National Corpus dataset. 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.

  Use "SlopeQ for BNC Search Engine"

• 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)"

• Korektor 2

  3 resources

  Korektor is a statistical spell-checker and (occasionally) grammar-checker. It is released under 2-Clause BSD license http://opensource.org/licenses/BSD-2-Clause. Korektor started with Michal Richter's diploma thesis Advanced Czech Spellchecker https://redmine.ms.mff.cuni.cz/documents/1, but it is being developed further. There are two versions: a command line utility (tested on Linux, Windows and OS X) and a REST service with publicly available API http://lindat.mff.cuni.cz/services/korektor/api-reference.php and HTML front end https://lindat.mff.cuni.cz/services/korektor/.

  Use "Korektor 2"

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

  3 resources

  CUBBITT En-Cs 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->cs: 27.6 cs->en: 34.4 (Evaluated using multeval: https://github.com/jhclark/multeval)

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

• Opener Tokenizer

  1 resources

  Tokenizer for Dutch, English, German, French, Spanish and Italian. Consumes Plain text and produces TCF.

• Wikipedia Search EN

  1 resources

  Wikipedia is an online free-content encyclopedia that you can edit and contribute to. Wikipedia co-founder Jimmy Wales has described Wikipedia as "an effort to create and distribute a free encyclopedia of the highest possible quality to every single person on the planet in their own language." Wikipedia exists to bring knowledge to everyone who seeks it.

• WebLicht POSTags Lemmas EN

  1 resources

  WebLicht Easy Chain for POS Tagging and Lemmatization (English). The pipeline makes use of WebLicht's TCF converter, the Stanford tokenizer, the Jitar POS Tagger, and the lemmatizer service from MorphAdorner. WebLicht's Tundra can be used to visualize the result.

• WebLicht NamedEntities EN

  1 resources

  WebLicht Easy Chain for Named Entity Recognition (English). The pipeline makes use of WebLicht's TCF converter, the Stanford tokenizer, and the Illinois Named Entity Recognizer. WebLicht's Tundra can be used to visualize the result.