Edit model card

gelectra-base for Extractive QA

Overview

Language model: gelectra-base-germanquad
Language: German
Training data: GermanQuAD train set (~ 12MB)
Eval data: GermanQuAD test set (~ 5MB)
Infrastructure: 1x V100 GPU
Code: See an example extractive QA pipeline built with Haystack
Published: Apr 21st, 2021

Details

  • We trained a German question answering model with a gelectra-base model as its basis.
  • The dataset is GermanQuAD, a new, German language dataset, which we hand-annotated and published online.
  • The training dataset is one-way annotated and contains 11518 questions and 11518 answers, while the test dataset is three-way annotated so that there are 2204 questions and with 2204·3−76 = 6536answers, because we removed 76 wrong answers.

See https://deepset.ai/germanquad for more details and dataset download in SQuAD format.

Hyperparameters

batch_size = 24
n_epochs = 2
max_seq_len = 384
learning_rate = 3e-5
lr_schedule = LinearWarmup
embeds_dropout_prob = 0.1

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/gelectra-base-germanquad")
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/gelectra-base-germanquad"

# 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

We evaluated the extractive question answering performance on our GermanQuAD test set. Model types and training data are included in the model name. For finetuning XLM-Roberta, we use the English SQuAD v2.0 dataset. The GELECTRA models are warm started on the German translation of SQuAD v1.1 and finetuned on GermanQuAD. The human baseline was computed for the 3-way test set by taking one answer as prediction and the other two as ground truth.
performancetable

Authors

Timo Möller: [email protected]
Julian Risch: [email protected]
Malte Pietsch: [email protected]

About us

deepset is the company behind the production-ready open-source AI framework Haystack.

Some of our other work:

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
1,783
Safetensors
Model size
109M params
Tensor type
I64
·
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train deepset/gelectra-base-germanquad

Spaces using deepset/gelectra-base-germanquad 2