Roberta Base Squad2

🚀 roberta-base for QA

This model is designed for extractive question-answering tasks in English, leveraging the roberta-base language model and trained on the SQuAD 2.0 dataset.

🚀 Quick Start

NOTE: This is version 2 of the model. See this github issue from the FARM repository for an explanation of why we updated. If you'd like to use version 1, specify revision="v1.0" when loading the model in Transformers 3.5. For example:

model_name = "deepset/roberta-base-squad2"
pipeline(model=model_name, tokenizer=model_name, revision="v1.0", task="question-answering")

✨ Features

• Language model: roberta-base
• Language: English
• Downstream-task: Extractive QA
• Training data: SQuAD 2.0
• Eval data: SQuAD 2.0
• Code: See example in FARM
• Infrastructure: 4x Tesla v100

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

In Transformers

from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline

model_name = "deepset/roberta-base-squad2"

# a) Get predictions
nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)
QA_input = {
    'question': 'Why is model conversion important?',
    'context': 'The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.'
}
res = nlp(QA_input)

# b) Load model & tokenizer
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

In FARM

from farm.modeling.adaptive_model import AdaptiveModel
from farm.modeling.tokenization import Tokenizer
from farm.infer import Inferencer

model_name = "deepset/roberta-base-squad2"

# a) Get predictions
nlp = Inferencer.load(model_name, task_type="question_answering")
QA_input = [{"questions": ["Why is model conversion important?"],
             "text": "The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks."}]
res = nlp.inference_from_dicts(dicts=QA_input, rest_api_schema=True)

# b) Load model & tokenizer
model = AdaptiveModel.convert_from_transformers(model_name, device="cpu", task_type="question_answering")
tokenizer = Tokenizer.load(model_name)

In haystack

For doing QA at scale (i.e. many docs instead of single paragraph), you can load the model also in haystack:

reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2")
# or 
reader = TransformersReader(model_name_or_path="deepset/roberta-base-squad2",tokenizer="deepset/roberta-base-squad2")

Advanced Usage

No advanced usage examples are provided in the original document.

📚 Documentation

Hyperparameters

batch_size = 96
n_epochs = 2
base_LM_model = "roberta-base"
max_seq_len = 386
learning_rate = 3e-5
lr_schedule = LinearWarmup
warmup_proportion = 0.2
doc_stride=128
max_query_length=64

Using a distilled model instead

Please note that we have also released a distilled version of this model called deepset/tinyroberta-squad2. The distilled model has a comparable prediction quality and runs at twice the speed of the base model.

Performance

Evaluated on the SQuAD 2.0 dev set with the official eval script.

"exact": 79.87029394424324,
"f1": 82.91251169582613,

"total": 11873,
"HasAns_exact": 77.93522267206478,
"HasAns_f1": 84.02838248389763,
"HasAns_total": 5928,
"NoAns_exact": 81.79983179142137,
"NoAns_f1": 81.79983179142137,
"NoAns_total": 5945

🔧 Technical Details

No additional technical details are provided in the original document.

📄 License

This model is released under the cc-by-4.0 license.

👥 Authors

• Branden Chan: branden.chan [at] deepset.ai
• Timo Möller: timo.moeller [at] deepset.ai
• Malte Pietsch: malte.pietsch [at] deepset.ai
• Tanay Soni: tanay.soni [at] deepset.ai

👋 About Us

We bring NLP to the industry via open source!
Our focus: Industry specific language models & large scale QA systems.

Some of our work:

• German BERT (aka "bert-base-german-cased")
• GermanQuAD and GermanDPR datasets and models (aka "gelectra-base-germanquad", "gbert-base-germandpr")
• FARM
• Haystack

Get in touch: Twitter | LinkedIn | Slack | GitHub Discussions | Website

By the way: we're hiring!