Model Card for Model ID
language:
- es
license: mit
tags:
- text-classification
- intent-classification
- spanish
- colombian-spanish
- bert
- beto
- medical
- conversational
base_model: dccuchile/bert-base-spanish-wwm-cased
Model Details
Model Description
Fine-tuned version of BETO (dccuchile/bert-base-spanish-wwm-cased) for
intent classification in the context of medical appointment management
through voice in Colombian colloquial Spanish. Developed as part of the
undergraduate thesis project Medix at the Pontificia Universidad
Javeriana (Bogotá, Colombia).
- Developed by: Leonardo Velázquez, Diego Jara, Adrián Ruiz, Jairo Sierra
- Institution: Pontificia Universidad Javeriana — Facultad de Ingeniería
- Supervised by: Dra. Andrea Del Pilar Rueda-Olarte
- Model type: Text Classification (Intent Classification)
- Language: Spanish — Colombian colloquial variant (Bogotá dialect)
- License: MIT
- Finetuned from:
dccuchile/bert-base-spanish-wwm-cased
Model Sources
- Repository:
https://huggingface.co/Diego503/medix-nlu-intent-classifier
- Thesis project: TBA
Uses
Direct Use
This model classifies user utterances in Colombian colloquial Spanish into
one of seven intent classes for medical appointment management:
| Intent | Description |
|---|
agendar_cita | User requests to schedule a new medical appointment |
cancelar_cita | User wants to cancel an existing appointment |
reprogramar_cita | User wants to reschedule an existing appointment |
consultar_cita | User asks about availability before scheduling |
entrega_datos | User provides personal information (name, ID number) |
asentimiento_positivo | User confirms information presented by the system |
asentimiento_negativo | User rejects or corrects information |
Downstream Use [optional]
Designed to be integrated into a voice-based conversational pipeline:
- ASR (Faster-Whisper) transcribes user audio to text
- This model classifies the intent
- Rule-based entity extractor extracts medical specialty, date, and
patient identification
- TTS (edge-tts
es-CO-SalomeNeural) returns the system response
During inference, a label map (_BETO_LABEL_MAP) consolidates
entrega_datos, asentimiento_positivo and asentimiento_negativo
into a single functional class (provide_info), and maps consultar_cita
to check_availability.
Out-of-Scope Use
- Not intended for general-purpose Spanish NLU outside the medical
appointment domain
- Not validated for Spanish variants other than Colombian colloquial Spanish
- Not suitable for formal or neutral Spanish without retraining
[More Information Needed]
Bias, Risks, and Limitations
[More Information Needed]
Recommendations
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
[More Information Needed]
Training Procedure
Preprocessing [optional]
[More Information Needed]
Training Hyperparameters
- Training regime: [More Information Needed]
Speeds, Sizes, Times [optional]
[More Information Needed]
Evaluation
Testing Data, Factors & Metrics
Testing Data
[More Information Needed]
Factors
[More Information Needed]
Metrics
[More Information Needed]
Results
[More Information Needed]
Summary
Model Examination [optional]
[More Information Needed]
Environmental Impact
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]
BibTeX:
[More Information Needed]
APA:
[More Information Needed]
Glossary [optional]
[More Information Needed]
More Information [optional]
[More Information Needed]
Model Card Authors [optional]
[More Information Needed]
Model Card Contact
[More Information Needed]
