The Effect of Domain and Diacritics in Yoruba–English Neural Machine Translation

no code implementations • MTSummit 2021 • David Adelani, Dana Ruiter, Jesujoba Alabi, Damilola Adebonojo, Adesina Ayeni, Mofe Adeyemi, Ayodele Esther Awokoya, Cristina España-Bonet

Massively multilingual machine translation (MT) has shown impressive capabilities and including zero and few-shot translation between low-resource language pairs.

Machine Translation Translation

Transfer Learning and Distant Supervision for Multilingual Transformer Models: A Study on African Languages

1 code implementation • EMNLP 2020 • Michael A. Hedderich, David Adelani, Dawei Zhu, Jesujoba Alabi, Udia Markus, Dietrich Klakow

Multilingual transformer models like mBERT and XLM-RoBERTa have obtained great improvements for many NLP tasks on a variety of languages.

NER Topic Classification +1

Massive vs. Curated Embeddings for Low-Resourced Languages: the Case of Yor\`ub\'a and Twi

no code implementations • LREC 2020 • Jesujoba Alabi, Kwabena Amponsah-Kaakyire, David Adelani, Cristina Espa{\~n}a-Bonet

In this paper we focus on two African languages, Yor{\`u}b{\'a} and Twi, and compare the word embeddings obtained in this way, with word embeddings obtained from curated corpora and a language-dependent processing.

Named Entity Recognition Word Embeddings

Demographic Inference and Representative Population Estimates from Multilingual Social Media Data

no code implementations • 15 May 2019 • Zijian Wang, Scott A. Hale, David Adelani, Przemyslaw A. Grabowicz, Timo Hartmann, Fabian Flöck, David Jurgens

In a large experiment over multilingual heterogeneous European regions, we show that our demographic inference and bias correction together allow for more accurate estimates of populations and make a significant step towards representative social sensing in downstream applications with multilingual social media.