Search results

• Slovenian RoBERTa contextual embeddings model: SloBERTa 2.0

  3 resources

  The monolingual Slovene RoBERTa (A Robustly Optimized Bidirectional Encoder Representations from Transformers) model is a state-of-the-art model representing words/tokens as contextually dependent word embeddings, used for various NLP tasks. Word embeddings can be extracted for every word occurrence and then used in training a model for an end task, but typically the whole RoBERTa model is fine-tuned end-to-end. SloBERTa model is closely related to French Camembert model https://camembert-model.fr/. The corpora used for training the model have 3.47 billion tokens in total. The subword vocabulary contains 32,000 tokens. The scripts and programs used for data preparation and training the model are available on https://github.com/clarinsi/Slovene-BERT-Tool Compared with the previous version (1.0), this version was trained for further 61 epochs (v1.0 37 epochs, v2.0 98 epochs), for a total of 200,000 iterations/updates. The released model here is a pytorch neural network model, intended for usage with the transformers library https://github.com/huggingface/transformers (sloberta.2.0.transformers.tar.gz) or fairseq library https://github.com/pytorch/fairseq (sloberta.2.0.fairseq.tar.gz)

  Use "Slovenian RoBERTa contextual embeddings model: SloBERTa 2.0"

• CroSloEngual BERT

  4 resources

  Trilingual BERT (Bidirectional Encoder Representations from Transformers) model, trained on Croatian, Slovenian, and English data. State of the art tool representing words/tokens as contextually dependent word embeddings, used for various NLP classification tasks by finetuning the model end-to-end. CroSloEngual BERT are neural network weights and configuration files in pytorch format (ie. to be used with pytorch library).

  Use "CroSloEngual BERT"

• LVBERT - Latvian BERT

  4 resources

  LVBERT is the first publicly available monolingual BERT language model pre-trained for Latvian. For training we used the original implementation of BERT on TensorFlow with the whole-word masking and the next sentence prediction objectives. We used BERT-BASE configuration with 12 layers, 768 hidden units, 12 heads, 128 sequence length, 128 mini-batch size and 32,000 token vocabulary.

  Use "LVBERT - Latvian BERT"

• CroSloEngual BERT 1.1

  4 resources

  Trilingual BERT (Bidirectional Encoder Representations from Transformers) model, trained on Croatian, Slovenian, and English data. State of the art tool representing words/tokens as contextually dependent word embeddings, used for various NLP classification tasks by finetuning the model end-to-end. CroSloEngual BERT are neural network weights and configuration files in pytorch format (i.e. to be used with pytorch library). Changes in version 1.1: fixed vocab.txt file, as previous verson had an error causing very bad results during fine-tuning and/or evaluation.

  Use "CroSloEngual BERT 1.1"

• Slovenian RoBERTa contextual embeddings model: SloBERTa 1.0

  5 resources

  The monolingual Slovene RoBERTa (A Robustly Optimized Bidirectional Encoder Representations from Transformers) model is a state-of-the-art model representing words/tokens as contextually dependent word embeddings, used for various NLP tasks. Word embeddings can be extracted for every word occurrence and then used in training a model for an end task, but typically the whole RoBERTa model is fine-tuned end-to-end. SloBERTa model is closely related to French Camembert model https://camembert-model.fr/. The corpora used for training the model have 3.47 billion tokens in total. The subword vocabulary contains 32,000 tokens. The scripts and programs used for data preparation and training the model are available on https://github.com/clarinsi/Slovene-BERT-Tool The released model here is a pytorch neural network model, intended for usage with the transformers library https://github.com/huggingface/transformers.

  Use "Slovenian RoBERTa contextual embeddings model: SloBERTa 1.0"

• LitLat BERT

  4 resources

  Trilingual BERT-like (Bidirectional Encoder Representations from Transformers) model, trained on Lithuanian, Latvian, and English data. State of the art tool representing words/tokens as contextually dependent word embeddings, used for various NLP classification tasks by fine-tuning the model end-to-end. LitLat BERT are neural network weights and configuration files in pytorch format (i.e. to be used with pytorch library). The corpora used for training the model have 4.07 billion tokens in total, of which 2.32 billion are English, 1.21 billion are Lithuanian and 0.53 billion are Latvian. LitLat BERT is based on XLM-RoBERTa model and comes in two versions, one for usage with transformers library (https://github.com/huggingface/transformers), and one for usage with fairseq library (https://github.com/pytorch/fairseq). More information is in the readme.txt.

  Use "LitLat BERT"