Roberta Large

🚀 RoBERTa large model

A pre - trained model on English using masked language modeling (MLM) objective, which can extract useful features for downstream tasks.

🚀 Quick Start

This RoBERTa large model is pre - trained on English language with MLM objective. It can be used for masked language modeling directly or fine - tuned on downstream tasks.

✨ Features

• Bidirectional Representation: Learns a bidirectional representation of sentences through masked language modeling, different from traditional RNNs and autoregressive models.
• Feature Extraction: Can learn an inner representation of the English language, which can be used to extract features for downstream tasks.
• Fine - Tuning Capability: Primarily intended to be fine - tuned on downstream tasks such as sequence classification, token classification, or question answering.

📦 Installation

The installation details are not provided in the original document. You can refer to the official transformers library for installation.

💻 Usage Examples

Basic Usage

You can use this model directly with a pipeline for masked language modeling:

>>> from transformers import pipeline
>>> unmasker = pipeline('fill - mask', model='roberta - large')
>>> unmasker("Hello I'm a <mask> model.")

[{'sequence': "<s>Hello I'm a male model.</s>",
  'score': 0.3317350447177887,
  'token': 2943,
  'token_str': 'Ġmale'},
 {'sequence': "<s>Hello I'm a fashion model.</s>",
  'score': 0.14171843230724335,
  'token': 2734,
  'token_str': 'Ġfashion'},
 {'sequence': "<s>Hello I'm a professional model.</s>",
  'score': 0.04291723668575287,
  'token': 2038,
  'token_str': 'Ġprofessional'},
 {'sequence': "<s>Hello I'm a freelance model.</s>",
  'score': 0.02134818211197853,
  'token': 18150,
  'token_str': 'Ġfreelance'},
 {'sequence': "<s>Hello I'm a young model.</s>",
  'score': 0.021098261699080467,
  'token': 664,
  'token_str': 'Ġyoung'}]

Advanced Usage

Here is how to use this model to get the features of a given text in PyTorch:

from transformers import RobertaTokenizer, RobertaModel
tokenizer = RobertaTokenizer.from_pretrained('roberta - large')
model = RobertaModel.from_pretrained('roberta - large')
text = "Replace me by any text you'd like."
encoded_input = tokenizer(text, return_tensors='pt')
output = model(**encoded_input)

And in TensorFlow:

from transformers import RobertaTokenizer, TFRobertaModel
tokenizer = RobertaTokenizer.from_pretrained('roberta - large')
model = TFRobertaModel.from_pretrained('roberta - large')
text = "Replace me by any text you'd like."
encoded_input = tokenizer(text, return_tensors='tf')
output = model(encoded_input)

📚 Documentation

Intended uses & limitations

You can use the raw model for masked language modeling, but it's mostly intended to be fine - tuned on a downstream task. See the model hub to look for fine - tuned versions on a task that interests you.

Note that this model is primarily aimed at being fine - tuned on tasks that use the whole sentence (potentially masked) to make decisions, such as sequence classification, token classification or question answering. For tasks such as text generation you should look at model like GPT2.

Limitations and bias

The training data used for this model contains a lot of unfiltered content from the internet, which is far from neutral. Therefore, the model can have biased predictions:

>>> from transformers import pipeline
>>> unmasker = pipeline('fill - mask', model='roberta - large')
>>> unmasker("The man worked as a <mask>.")

[{'sequence': '<s>The man worked as a mechanic.</s>',
  'score': 0.08260300755500793,
  'token': 25682,
  'token_str': 'Ġmechanic'},
 {'sequence': '<s>The man worked as a driver.</s>',
  'score': 0.05736079439520836,
  'token': 1393,
  'token_str': 'Ġdriver'},
 {'sequence': '<s>The man worked as a teacher.</s>',
  'score': 0.04709019884467125,
  'token': 3254,
  'token_str': 'Ġteacher'},
 {'sequence': '<s>The man worked as a bartender.</s>',
  'score': 0.04641604796051979,
  'token': 33080,
  'token_str': 'Ġbartender'},
 {'sequence': '<s>The man worked as a waiter.</s>',
  'score': 0.04239227622747421,
  'token': 38233,
  'token_str': 'Ġwaiter'}]

>>> unmasker("The woman worked as a <mask>.")

[{'sequence': '<s>The woman worked as a nurse.</s>',
  'score': 0.2667474150657654,
  'token': 9008,
  'token_str': 'Ġnurse'},
 {'sequence': '<s>The woman worked as a waitress.</s>',
  'score': 0.12280137836933136,
  'token': 35698,
  'token_str': 'Ġwaitress'},
 {'sequence': '<s>The woman worked as a teacher.</s>',
  'score': 0.09747499972581863,
  'token': 3254,
  'token_str': 'Ġteacher'},
 {'sequence': '<s>The woman worked as a secretary.</s>',
  'score': 0.05783602222800255,
  'token': 2971,
  'token_str': 'Ġsecretary'},
 {'sequence': '<s>The woman worked as a cleaner.</s>',
  'score': 0.05576248839497566,
  'token': 16126,
  'token_str': 'Ġcleaner'}]

This bias will also affect all fine - tuned versions of this model.

Training data

The RoBERTa model was pretrained on the reunion of five datasets:

• BookCorpus, a dataset consisting of 11,038 unpublished books;
• English Wikipedia (excluding lists, tables and headers);
• [CC - News](https://commoncrawl.org/2016/10/news - dataset - available/), a dataset containing 63 millions English news articles crawled between September 2016 and February 2019.
• OpenWebText, an opensource recreation of the WebText dataset used to train GPT - 2.
• Stories a dataset containing a subset of CommonCrawl data filtered to match the story - like style of Winograd schemas.

Together these datasets weight 160GB of text.

Training procedure

Preprocessing

The texts are tokenized using a byte version of Byte - Pair Encoding (BPE) and a vocabulary size of 50,000. The inputs of the model take pieces of 512 contiguous token that may span over documents. The beginning of a new document is marked with <s> and the end of one by </s>

The details of the masking procedure for each sentence are the following:

• 15% of the tokens are masked.
• In 80% of the cases, the masked tokens are replaced by <mask>.
• In 10% of the cases, the masked tokens are replaced by a random token (different) from the one they replace.
• In the 10% remaining cases, the masked tokens are left as is.

Contrary to BERT, the masking is done dynamically during pretraining (e.g., it changes at each epoch and is not fixed).

Pretraining

The model was trained on 1024 V100 GPUs for 500K steps with a batch size of 8K and a sequence length of 512. The optimizer used is Adam with a learning rate of 4e - 4, \(\beta_{1}=0.9\), \(\beta_{2}=0.98\) and \(\epsilon = 1e - 6\), a weight decay of 0.01, learning rate warmup for 30,000 steps and linear decay of the learning rate after.

Evaluation results

When fine - tuned on downstream tasks, this model achieves the following results:

Glue test results:

BibTeX entry and citation info

@article{DBLP:journals/corr/abs-1907-11692,
  author    = {Yinhan Liu and
               Myle Ott and
               Naman Goyal and
               Jingfei Du and
               Mandar Joshi and
               Danqi Chen and
               Omer Levy and
               Mike Lewis and
               Luke Zettlemoyer and
               Veselin Stoyanov},
  title     = {RoBERTa: {A} Robustly Optimized {BERT} Pretraining Approach},
  journal   = {CoRR},
  volume    = {abs/1907.11692},
  year      = {2019},
  url       = {http://arxiv.org/abs/1907.11692},
  archivePrefix = {arXiv},
  eprint    = {1907.11692},
  timestamp = {Thu, 01 Aug 2019 08:59:33 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-1907-11692.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

📄 License

This project is licensed under the MIT license.