Introducing various Semantic Models for Amharic: Experimentation and Evaluation with multiple Tasks and Datasets

1 code implementation • 2 Nov 2020 • Seid Muhie Yimam, Abinew Ali Ayele, Gopalakrishnan Venkatesh, Chris Biemann

We find that newly trained models perform better than pre-trained multilingual models.

Network Embedding

Analysis of the Ethiopic Twitter Dataset for Abusive Speech in Amharic

no code implementations • 9 Dec 2019 • Seid Muhie Yimam, Abinew Ali Ayele, Chris Biemann

Since several languages can be written using the Fidel script, we have used the existing Amharic, Tigrinya and Ge'ez corpora to retain only the Amharic tweets.