roberta-base for Extractive QA
This is the roberta-base model, fine-tuned using the SQuAD2.0 dataset. It's been trained on question-answer pairs, including unanswerable questions, for the task of Extractive Question Answering. We have also released a distilled version of this model called deepset/tinyroberta-squad2. It has a comparable prediction quality and runs at twice the speed of deepset/roberta-base-squad2.
Overview
Language model: roberta-base
Language: English
Downstream-task: Extractive QA
Training data: SQuAD 2.0
Eval data: SQuAD 2.0
Code: See an example extractive QA pipeline built with Haystack
Infrastructure: 4x Tesla v100
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
Usage
In Haystack
Haystack is an AI orchestration framework to build customizable, production-ready LLM applications. You can use this model in Haystack to do extractive question answering on documents. To load and run the model with Haystack:
# After running pip install haystack-ai "transformers[torch,sentencepiece]"
from haystack import Document
from haystack.components.readers import ExtractiveReader
docs = [
Document(content="Python is a popular programming language"),
Document(content="python ist eine beliebte Programmiersprache"),
]
reader = ExtractiveReader(model="deepset/roberta-base-squad2")
reader.warm_up()
question = "What is a popular programming language?"
result = reader.run(query=question, documents=docs)
# {'answers': [ExtractedAnswer(query='What is a popular programming language?', score=0.5740374326705933, data='python', document=Document(id=..., content: '...'), context=None, document_offset=ExtractedAnswer.Span(start=0, end=6),...)]}
For a complete example with an extractive question answering pipeline that scales over many documents, check out the corresponding Haystack tutorial.
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)
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
Authors
Branden Chan: [email protected]
Timo Möller: [email protected]
Malte Pietsch: [email protected]
Tanay Soni: [email protected]
About us
deepset is the company behind the production-ready open-source AI framework Haystack.
Some of our other work:
- Distilled roberta-base-squad2 (aka "tinyroberta-squad2")
- German BERT, GermanQuAD and GermanDPR, German embedding model
- deepset Cloud
- deepset Studio
Get in touch and join the Haystack community
For more info on Haystack, visit our GitHub repo and Documentation.
We also have a Discord community open to everyone!
Twitter | LinkedIn | Discord | GitHub Discussions | Website | YouTube
By the way: we're hiring!
- Downloads last month
- 713,908
Model tree for deepset/roberta-base-squad2
Base model
FacebookAI/roberta-baseDataset used to train deepset/roberta-base-squad2
Spaces using deepset/roberta-base-squad2 100
Evaluation results
- Exact Match on squad_v2validation set verified79.931
- F1 on squad_v2validation set verified82.950
- total on squad_v2validation set verified11869.000
- Exact Match on squadvalidation set self-reported85.289
- F1 on squadvalidation set self-reported91.841
- Exact Match on adversarial_qavalidation set self-reported29.500
- F1 on adversarial_qavalidation set self-reported40.367
- Exact Match on squad_adversarialvalidation set self-reported78.567
- F1 on squad_adversarialvalidation set self-reported84.469
- Exact Match on squadshifts amazontest set self-reported69.924