activity
20172025
most citedAdapting Pre-trained Language Models to African Languages via Multilingual Adaptive Fine-Tuning

51 citations · 129 across the 61 of their papers we have counts for

collaborators
Showing 2022Show all

18 papers · 1 filter

cs.CL2022★ 3 cited

MasakhaNER 2.0: Africa-centric Transfer Learning for Named Entity Recognition

David Ifeoluwa Adelani, Graham Neubig, Sebastian Ruder +42

African languages are spoken by over a billion people, but are underrepresented in NLP research and development. The challenges impeding progress include the limited availability o…

cs.CL2022

A Data-Driven Investigation of Noise-Adaptive Utterance Generation with Linguistic Modification

Anupama Chingacham, Vera Demberg, Dietrich Klakow

In noisy environments, speech can be hard to understand for humans. Spoken dialog systems can help to enhance the intelligibility of their output, either by modifying the speech sy…

cs.CL2022

Integrating Form and Meaning: A Multi-Task Learning Model for Acoustic Word Embeddings

Badr M. Abdullah, Bernd Möbius, Dietrich Klakow

Models of acoustic word embeddings (AWEs) learn to map variable-length spoken word segments onto fixed-dimensionality vector representations such that different acoustic exemplars…

cs.CL2022★ 1 cited

Fusing Sentence Embeddings Into LSTM-based Autoregressive Language Models

Vilém Zouhar, Marius Mosbach, Dietrich Klakow

Although masked language models are highly performant and widely adopted by NLP practitioners, they can not be easily used for autoregressive language modelling (next word predicti…

cs.CL2022★ 1 cited

TOKEN is a MASK: Few-shot Named Entity Recognition with Pre-trained Language Models

Ali Davody, David Ifeoluwa Adelani, Thomas Kleinbauer +1

Transferring knowledge from one domain to another is of practical importance for many tasks in natural language processing, especially when the amount of available data in the targ…

cs.CL2022

Task-Adaptive Pre-Training for Boosting Learning With Noisy Labels: A Study on Text Classification for African Languages

Dawei Zhu, Michael A. Hedderich, Fangzhou Zhai +2

For high-resource languages like English, text classification is a well-studied task. The performance of modern NLP models easily achieves an accuracy of more than 90% in many stan…