BabelBot at AraFinNLP2024: Fine-tuning T5 for Multi-dialect Intent Detection with Synthetic Data and Model Ensembling
Domaine:
natural language processingType de record:
paper
Créateur:
AssFarTou
Éditeur:
Und
Hôte:
This paper presents our results for the Arabic Financial NLP (AraFinNLP) shared task at the Second Arabic Natural Language Processing Conference (ArabicNLP 2024). We participated in the first sub-task, Multi-dialect Intent Detection, which focused on cross-dialect intent detection in the banking domain. Our approach involved fine-tuning an encoder-only T5 model, generating synthetic data, and model ensembling. Additionally, we conducted an in-depth analysis of the dataset, addressing annotation errors and problematic translations. Our model was ranked third in the shared task, achieving a F1-score of 0.871.
Similaires
Fine-Tuning Transformers and LLMs for Fake News Detection in Algerian DialectBrain Tumor Segmentation in Sub-Sahara Africa with Advanced Transformer and ConvNet Methods: Fine-Tuning, Data Mixing and EnsemblingSequential Fine-Tuning with Typologically Similar Languages for Yoruba Euphemism DetectionMultilingual Multi-Label Emotion Classification at Scale with Synthetic Data**Scaling Model Size and Fine-Tuning Strategies in Cross-Lingual Euphemism Detection**Overcoming Data Scarcity in Multi-Dialectal Arabic ASR via Whisper Fine-Tuning