Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

kobeoseijnr/Few-Shot-Sentiment-Learning-with-Synthetic-Augmentation-in-Low-Resource-Settings

Domaine:

natural language processing

Type de record:

project
Créateur:
kob
Hôte:
Few Shot Sentiment Learning with Synthetic Augmentation in Low Resource Settings # Few-Shot Sentiment Learning in Low-Resource Settings This project performs sentiment classification on Hausa language data using a few-shot learning setup enhanced with back-translation for data augmentation. ## Features - Multilingual Transformer Fine-tuning - Synthetic Augmentation via Back-Translation - Evaluation using Accuracy, F1, Confusion Matrix, BLEU, and BERTScore ## Setup ```bash pip install -r requirements.txt ``` ## Usage ```bash jupyter notebook few-shot-learning.ipynb ``` ## Structure - `few-shot-learning.ipynb` — Main notebook for training and evaluation - `data/` — Input dataset directory - `augmented/` — Back-translated data - `outputs/` — Evaluation results and plots ## License MIT License

Visit

github.com

Tasks

machine translationsentiment analysistext classification

Languages

Hausa

Similaires

Visually grounded few-shot word learning in low-resource settingsSynthetic Query Augmentation for Zero-Shot Cross-Lingual Dense Retrieval in Low-Resource LanguagesMulti-Positive Contrastive Learning with Synthetic Misspelling Augmentation for Cross-Lingual Dense Retrievers in Low-ResourceCross-lingual NER Annotation Projection vs. Zero-Shot Few-Shot Learning in Low-Resource LanguagesSelf-training vs Few-shot Learning in Cross-lingual NER for Low-resource LanguagesLLMs Are Few-Shot In-Context Low-Resource Language Learners

Visually grounded few-shot word learning in low-resource settings

We propose a visually grounded speech model that learns new words and their visual depictions from j

Synthetic Query Augmentation for Zero-Shot Cross-Lingual Dense Retrieval in Low-Resource Languages

Multilingual Pretrained Language Models (MPLMs) perform strongly in cross-lingual transfer. We propo

Multi-Positive Contrastive Learning with Synthetic Misspelling Augmentation for Cross-Lingual Dense Retrievers in Low-Resource

Dense retrieval has become the new paradigm in passage retrieval. Despite its effectiveness on typo-

Cross-lingual NER Annotation Projection vs. Zero-Shot Few-Shot Learning in Low-Resource Languages

Cross-lingual Named Entity Recognition (NER) leverages knowledge transfer between languages to ident

Self-training vs Few-shot Learning in Cross-lingual NER for Low-resource Languages

Cross-lingual Named Entity Recognition (NER) leverages knowledge transfer between languages to ident

LLMs Are Few-Shot In-Context Low-Resource Language Learners

In-context learning (ICL) empowers large language models (LLMs) to perform diverse tasks in underrep