Result filters

Metadata provider

Language

...more

Resource type

Availability

  • Non-commercial
  • Share-alike

Active filters:

  • Availability: Non-commercial
  • Availability: Share-alike
43 record(s) found

Search results

  • GrETEL Search Engine for Querying Syntactic Constructions in Treebanks

    GrETEL is a query engine in which linguists can use a natural language example as a starting point for searching a treebank with limited knowledge about tree representations and formal query languages. Instead of a formal search instruction, it takes a natural language example as input. This provides a convenient way for novice and non-technical users to use treebanks with a limited knowledge of the underlying syntax and formal query languages. By allowing linguists to search for constructions similar to the example they provide, it aims to bridge the gap between descriptive-theoretical and computational linguistics. The example-based query procedure consists of several steps. In the first step the user enters an example of the construction he/she is interested in. In the second step the example is returned in the form of a matrix, in which the user specifies which aspects of this example are essential for the construction under investigation. The third step provides an overview of the search instruction, i.e. the subpart of the parse tree that contains the elements relevant for the construction under investigation. This query tree is automatically converted in an XPath query which can be used for the actual treebank search. This query can be edited if desired. In the fourth step the query is executed on the selected corpus. The matching constructions are presented to the user as a list of sentences, which can be downloaded. The user can also click on the sentences in order to visualize the results as syntax trees. GrETEL enables search in the LASSY-SMALL and the CGN (Spoken Dutch Corpus) Treebanks (1 million tokens each). GrETEL was created by CLARIN Dutch Language Union in Flanders in the context of the CLARIN-NL / CLARIN Flanders cooperation project.
    Liesbeth Augustinus, Vincent Vandeghinste, and Frank Van Eynde (2012). "Example-Based Treebank Querying" In: Proceedings of the 8th International Conference on Language Resources and Evaluation (LREC-2012). Istanbul, Turkey. pp. 3161-3167
    Augustinus, L, Vandeghinste, V, Schuurman, I and Van Eynde, F. 2017. GrETEL: A Tool for Example-Based Treebank Mining. In: Odijk, J and van Hessen, A. (eds.) CLARIN in the Low Countries, Pp. 269–280. London: Ubiquity Press. DOI: https://doi.org/10.5334/bbi.22. License: CC-BY 4.0
    http://gretel.ccl.kuleuven.be/project/publications.php

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

    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!

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

    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)

  • Universal Dependencies 2.10 models for UDPipe 2 (2022-07-11)

    Tokenizer, POS Tagger, Lemmatizer and Parser models for 123 treebanks of 69 languages of Universal Depenencies 2.10 Treebanks, created solely using UD 2.10 data (https://hdl.handle.net/11234/1-4758). The model documentation including performance can be found at https://ufal.mff.cuni.cz/udpipe/2/models#universal_dependencies_210_models . To use these models, you need UDPipe version 2.0, which you can download from https://ufal.mff.cuni.cz/udpipe/2 .

  • PELCRA for National Corpus of Polish Search Engine 2

    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.