Result filters

Metadata provider

  • DSpace

Language

Resource type

Availability

Active filters:

  • Metadata provider: DSpace
  • Keywords: transformer
13 record(s) found

Search results

  • 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)

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

    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)

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

    CUBBITT En-Pl 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 newstest2020 (BLEU): en->pl: 12.3 pl->en: 20.0 (Evaluated using multeval: https://github.com/jhclark/multeval)

  • Translation Models (en-de) (v1.0)

    En-De 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 newstest2020 (BLEU): en->de: 25.9 de->en: 33.4 (Evaluated using multeval: https://github.com/jhclark/multeval)

  • MCSQ Translation Models (en-de) (v1.0)

    En-De translation models, exported via TensorFlow Serving, available in the Lindat translation service (https://lindat.mff.cuni.cz/services/translation/). The models were trained using the MCSQ social surveys dataset (available at https://repo.clarino.uib.no/xmlui/bitstream/handle/11509/142/mcsq_v3.zip). Their main use should be in-domain translation of social surveys. 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 MCSQ test set (BLEU): en->de: 67.5 (train: genuine in-domain MCSQ data only) de->en: 75.0 (train: additional in-domain backtranslated MCSQ data) (Evaluated using multeval: https://github.com/jhclark/multeval)

  • MCSQ Translation Models (en-ru) (v1.0)

    En-Ru translation models, exported via TensorFlow Serving, available in the Lindat translation service (https://lindat.mff.cuni.cz/services/translation/). The models were trained using the MCSQ social surveys dataset (available at https://repo.clarino.uib.no/xmlui/bitstream/handle/11509/142/mcsq_v3.zip). Their main use should be in-domain translation of social surveys. 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 MCSQ test set (BLEU): en->ru: 64.3 (train: genuine in-domain MCSQ data) ru->en: 74.7 (train: additional backtranslated in-domain MCSQ data) (Evaluated using multeval: https://github.com/jhclark/multeval)

  • Translation Models (en-ru) (v1.0)

    En-Ru 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 newstest2020 (BLEU): en->ru: 18.0 ru->en: 30.4 (Evaluated using multeval: https://github.com/jhclark/multeval)

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

    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!

  • Icelandic NER API - Ensamble model (21.09)

    A dockerized Named Entity Recognition (NER) API for Icelandic. It uses a the IceBERT language model from Miðeind as its primary model, but it also offers the possibility to use 3 other transformer language models with it ( ELECTRA-base, convbert-small, and multilingual-BERT) and combines them with CombiTagger. They were all fine tuned for NER using MIM-GOLD-NER. IceBERT was the best individual model as it achieves F1-score of ~92.73 on the test set for MIM-GOLD-NER, while the combination of the four, in the form of CombiTagger, achieved F1-score of 93.21. The code for the API is available at https://github.com/icelandic-lt/Icelandic-NER-API and the files for the fine tuned models are available in this submission. Dockerútfærð forritaskil fyrir nafnakennsl (NER) á íslensku. Þau notast við IceBERT mállíkan frá Miðeind sem sitt megin líkan, en þau bjóða líka upp á möguleikann að láta IceBERT vinna með 3 öðrum líkönum (ELECTRA-base, convbert-small og multilingual-BERT). Þau hafa öll verið fínstillt fyrir NER með nafnakennslamálheildinni MIM-GOLD-NER. Ef við skoðum hvert líkan fyrir sig, þá er IceBERT líkanið best, en það nær 92.73 í F1, á meðn CombiTagger nær 93.21 í F1. Forritunarkóðinn fyrir forritaskilinu eru aðgengileg hérna: https://github.com/icelandic-lt/Icelandic-NER-API og skrárnar fyrir fínstilltu líkönin má finna í þessari færslu.