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

  Authors

Libovický, Jindřich ; Rosa, Rudolf ; Helcl, Jindřich and Popel, Martin

  Item identifier

http://hdl.handle.net/11234/1-2839

 Project URL

https://ufal.mff.cuni.cz/grants/lsd

 Demo URL

https://ufal.mff.cuni.cz/grants/lsd

 Referenced by

http://ceur-ws.org/Vol-2203/138.pdf

 Date issued

2018-07-13

 Type

toolService

 Language(s)

Czech , English

 Description

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!

 Publisher

Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)

 Acknowledgement

GA ČR

Project code: 18-02196S

Project name: Reprezentace lingvistické struktury v neuronových sítích

 

Ministerstvo školství, mládeže a tělovýchovy České republiky

Project code: LM2015071

Project name: LINDAT/CLARIN: Institut pro analýzu, zpracování a distribuci lingvistických dat

 

Ministerstvo školství, mládeže a tělovýchovy České republiky

Project code: CZ.02.1.01/0.0/0.0/16_013/0001781

Project name: LINDAT/CLARIN - Výzkumná infrastruktura pro jazykové technologie - rozšíření repozitáře a výpočetní kapacity

 

Univerzita Karlova (mimo GAUK)

Project code: SVV 260 453

Project name: Specifický vysokoškolský výzkum

 

GAUK

Project code: 976518

Project name: Využití lingvistické informace v neuronovém strojovém překladu

 Subject(s)

sentiment analysis machine translation image captioning neural networks transformer Neural Monkey

 Collection(s)

LINDAT / CLARIAH-CZ Data & Tools

 

This item is replaced by a newer submission:

http://hdl.handle.net/11234/1-3145

List all versions  

Show full item record