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!
This submission contains trained end-to-end models for the Neural Monkey toolkit for Czech and English, solving four NLP tasks: machine translation, image captioning, sentiment analysis, and summarization.
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
In addition to the models presented in the referenced paper (developed and published in 2018), we include models for automatic news summarization for Czech and English developed in 2019. The Czech models were trained using the SumeCzech dataset (https://www.aclweb.org/anthology/L18-1551.pdf), the English models were trained using the CNN-Daily Mail corpus (https://arxiv.org/pdf/1704.04368.pdf) using the standard recurrent sequence-to-sequence architecture.
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
The summarization models require input that is tokenized with Moses Tokenizer (https://github.com/alvations/sacremoses) and lower-cased.
Feel free to contact the authors of this submission in case you run into problems!
Source code of the LINDAT Translation service frontend. The service provides a UI and a simple rest api that accesses machine translation models served by tensorflow serving.
The most recent version of the code is available at https://github.com/ufal/lindat_translation.
NameTag 2 is a named entity recognition tool. It recognizes named entities (e.g., names, locations, etc.) and can recognize both flat and embedded (nested) entities. NameTag 2 can be used either as a commandline tool or by requesting the NameTag webservice.
NameTag webservice can be found at:
https://lindat.mff.cuni.cz/services/nametag/
NameTag commandline tool can be downloaded from NameTag GitHub repository, branch nametag2:
git clone https://github.com/ufal/nametag -b nametag2
Latest models and documentation can be found at:
https://ufal.mff.cuni.cz/nametag/2
This software subject to the terms of the Mozilla Public License, v. 2.0 (http://mozilla.org/MPL/2.0/). The associated models are distributed under CC BY-NC-SA license.
Please cite as:
Jana Straková, Milan Straka, Jan Hajič (2019): Neural Architectures for Nested NER through Linearization. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 5326-5331, Association for Computational Linguistics, Stroudsburg, PA, USA, ISBN 978-1-950737-48-2 (https://aclweb.org/anthology/papers/P/P19/P19-1527/)
A simple way of browsing CoNLL format files in your terminal. Fast and text-based.
To open a CoNLL file, simply run: ./view_conll sample.conll
The output is piped through less, so you can use less commands to navigate the
file; by default the less searches for sentence beginnings, so you can use "n"
to go to next sentence and "N" to go to previous sentence. Close by "q". Trees
with a high number of non-projective edges may be difficult to read, as I have
not found a good way of displaying them intelligibly.
If you are on Windows and don't have less (but have Python), run like this: python view_conll.py sample.conll
For complete instructions, see the README file.
You need Python 2 to run the viewer.
Tokenizer, POS Tagger, Lemmatizer and Parser models for all 50 languages of Universal Depenencies 2.0 Treebanks, created solely using UD 2.0 data (http://hdl.handle.net/11234/1-1983). The model documentation including performance can be found at http://ufal.mff.cuni.cz/udpipe/users-manual#universal_dependencies_20_models .
To use these models, you need UDPipe binary version at least 1.2, which you can download from http://ufal.mff.cuni.cz/udpipe .
In addition to models itself, all additional data and value of hyperparameters used for training are available in the second archive, allowing reproducible training.
Ministerstvo školství, mládeže a tělovýchovy České republiky@@CZ.02.1.01/0.0/0.0/16_013/0001781@@LINDAT/CLARIN - Výzkumná infrastruktura pro jazykové technologie - rozšíření repozitáře a výpočetní kapacity@@nationalFunds@@✖[remove]7