xlm-roberta-large-expl-extraction-multi

---

license: cc-by-4.0 language:

• es tags:
• casimedicos
• explainability
• medical exams
• medical question answering
• extractive question answering
• squad
• multilinguality
• LLMs
• LLM pretty_name: mdeberta-expl-extraction-multi task_categories:
• question-answering size_categories:
• 1K<n<10K

---

<p align="center"> <br> <img src="http://www.ixa.eus/sites/default/files/anitdote.png" style="height: 200px;"> <br>

mdeberta-v3-base finetuned for Explanatory Argument Extraction

We finetuned mdeberta-v3-base on a novel extractive task which consists of identifying the explanation of the correct answer written by medical doctors in medical exams.

The training data is based on Antidote CasiMedicos for EN,ES,FR,IT languages.

The data source consists of Resident Medical Intern or Médico Interno Residente (MIR) exams, originally created by CasiMedicos, a Spanish community of medical professionals who collaboratively, voluntarily, and free of charge, publishes written explanations about the possible answers included in the MIR exams. The aim is to generate a resource that helps future medical doctors to study towards the MIR examinations. The commented MIR exams, including the explanations, are published in the CasiMedicos Project MIR 2.0 website.

We have extracted, clean, structure and annotated the available data so that each document in casimedicos-squad includes the clinical case, the correct answer, the multiple-choice questions and the commented exam written by native Spanish medical doctors. The comments have been annotated with the span in the text that corresponds to the explanation of the correct answer (see example below).

<table style="width:33%"> <tr> <th>casimedicos-squad splits</th> <tr> <td>train</td> <td>404</td> </tr> <tr> <td>validation</td> <td>56</td> </tr> <tr> <td>test</td> <td>119</td> </tr> </table>

Example

<p align="center"> <img src="https://github.com/ixa-ehu/antidote-casimedicos/blob/main/casimedicos-exp.png?raw=true" style="height: 650px;"> </p>

The example above shows a document in CasiMedicos containing the textual content, including Clinical Case (C), Question (Q), Possible Answers (P), and Explanation (E). Furthermore, for casimedicos-squad we annotated the span in the explanation (E) that corresponds to the correct answer (A).

The process of manually annotating the corpus consisted of specifying where the explanations of the correct answers begin and end. In order to obtain grammatically complete correct answer explanations, annotating full sentences or subordinate clauses was preferred over shorter spans.

Data Explanation

The dataset is structured as a list of documents ("paragraphs") where each of them include:

• context: the explanation (E) in the document
• qas: list of possible answers and questions. This element contains:
  • answers: an answer which corresponds to the explanation of the correct answer (A)
  • question: the clinical case (C) and question (Q)
  • id: unique identifier for the document

Citation

If you use this data please cite the following paper:

@misc{goenaga2023explanatory,
      title={Explanatory Argument Extraction of Correct Answers in Resident Medical Exams}, 
      author={Iakes Goenaga and Aitziber Atutxa and Koldo Gojenola and Maite Oronoz and Rodrigo Agerri},
      year={2023},
      eprint={2312.00567},
      archivePrefix={arXiv}
}

Contact: Iakes Goenaga and Rodrigo Agerri HiTZ Center - Ixa, University of the Basque Country UPV/EHU

Model Description

• 📖 Paper:Explanatory Argument Extraction of Correct Answers in Resident Medical Exams
• 💻 Github Repo (Data and Code): https://github.com/ixa-ehu/antidote-casimedicos
• 🌐 Project Website: https://univ-cotedazur.eu/antidote
• Funding: CHIST-ERA XAI 2019 call. Antidote (PCI2020-120717-2) funded by MCIN/AEI /10.13039/501100011033 and by European Union NextGenerationEU/PRTR
• Language(s) (NLP): EN,ES,FR,IT
• License: Apache License 2
• Finetuned from model: microsoft/mdeberta-v3-base

Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

[More Information Needed]

Downstream Use [optional]

<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->

[More Information Needed]

Out-of-Scope Use

<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->

[More Information Needed]

Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

[More Information Needed]

Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

[More Information Needed]

Training Procedure

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

• Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->

Speeds, Sizes, Times [optional]

<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->

[More Information Needed]

Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

Testing Data, Factors & Metrics

Testing Data

<!-- This should link to a Dataset Card if possible. -->

[More Information Needed]

Factors

<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->

[More Information Needed]

Metrics

<!-- These are the evaluation metrics being used, ideally with a description of why. -->

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

<!-- Relevant interpretability work for the model goes here -->

[More Information Needed]

Environmental Impact

<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

• Hardware Type: [More Information Needed]
• Hours used: [More Information Needed]
• Cloud Provider: [More Information Needed]
• Compute Region: [More Information Needed]
• Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]