Pinned Repositories
afriberta
AfriBERTa: Exploring the Viability of Pretrained Multilingual Language Models for Low-resourced Languages
africanlp-resources
List of all the resources I developed in collaboration with LSV and Masakhane during my doctoral studies and beyond
BERT-NER
Use Google's BERT for named entity recognition (CoNLL-2003 as the dataset).
How-to-distill-your-BERT
Code for the paper: How to Distill your BERT: An Empirical Study on the Impact of Weight Initialisation and Distillation Objectives (ACL 2023)
hstm
Code and data for "Heterogeneous Supervised Topic Models"
menyo-20k_MT
nepali-ner
Nepali NER dataset and code
NLP_DL_Intro
Deep learning for NLP
sib-200
SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects
yoruba-text
Yorùbá language training text for NLP, ASR and TTS tasks
dadelani's Repositories
dadelani/menyo-20k_MT
dadelani/afriberta
AfriBERTa: Exploring the Viability of Pretrained Multilingual Language Models for Low-resourced Languages
dadelani/academic-budget-bert
dadelani/africa-ner
dadelani/africanlp-public-datasets
A repository for publicly/freely available Natural Language Processing (NLP) datasets for African languages.
dadelani/AMMIcourse
dadelani/bbc-crawler-1
dadelani/CrossNER
CrossNER: Evaluating Cross-Domain Named Entity Recognition (AAAI-2021)
dadelani/delete_retrieve_generate
PyTorch implementation of the Delete, Retrieve Generate style transfer algorithm
dadelani/Few-NERD
Few-NERD
dadelani/FewShotTagging
Code for ACL2020 paper: Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network
dadelani/langrank
A program to choose transfer languages for cross-lingual learning
dadelani/LOTClass
[EMNLP 2020] Text Classification Using Label Names Only: A Language Model Self-Training Approach
dadelani/MedDG
a large-scale high-quality medical dialogue dataset
dadelani/medical_intent_detector_using_BERT
I built a multi-class classifier using BERT from Transformers that can identify common medical symptoms based on descriptive text.
dadelani/meta_cross_nlu_qa
Code for reproducing meta-learning for cross-lingual transfer learning in NLU and QA
dadelani/meta_learning_multilingual_doc_classification
Placeholder repository
dadelani/mulda
dadelani/newlang-tech
A guide to building language technology in new languages.
dadelani/PATR
This project provides the bash for datasets used in "Privacy-aware Text Rewriting" (INLG19).
dadelani/pii_hackhaton
dadelani/robust-maml
dadelani/structshot
Simple and Effective Few-Shot Named Entity Recognition with Structured Nearest Neighbor Learning
dadelani/style-transfer-paraphrase
Official code and data repository for our EMNLP 2020 long paper "Reformulating Unsupervised Style Transfer as Paraphrase Generation" (https://arxiv.org/abs/2010.05700).
dadelani/style-transformer
dadelani/synpg
Code for our EACL-2021 paper "Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairs".
dadelani/templateNER
Source code for template-based NER
dadelani/tomotopy
Python package of Tomoto, the Topic Modeling Tool
dadelani/TRANSLIT
dadelani/XLM
PyTorch original implementation of Cross-lingual Language Model Pretraining.