Pretrain RoBERTa for Spanish from scratch and perform NER on Spanish documents

BERTweet: A pre-trained language model for English Tweets (EMNLP-2020)

AfriBERTa: Exploring the Viability of Pretrained Multilingual Language Models for Low-resourced Languages

This is a repository for NaijaSenti. A Lacuna Funded Project for the development of sentiment corpus for four Nigerian languages: Igbo, Hausa, Yoruba and Pidgin.

AfriSenti-SemEval Shared Task 12: Sentiment Analysis for African languages : https://afrisenti-semeval.github.io/

Joint Bilingual Sentiment Embeddings and Classifier

BERT-based nominal Semantic Role Labeling (SRL), both using the Nombank dataset and the Ontonotes dataset.

[COLING'22] Code for "Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Arguments".

Stand-alone language identification system