51 citations · 129 across the 61 of their papers we have counts for
18 papers · 1 filter
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…
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…
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…
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…
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…
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…