Wietse de Vries

Neural Representations for Modeling Variation in English Speech.

2020 · arXiv (Cornell University)

Variation in speech is often represented and investigated using phonetic transcriptions, but transcribing speech is time-consuming and error prone. To create reliable representations of speech independent from phonetic transcriptions, we investigate the extraction of acoustic …

BERTje: A Dutch BERT Model

2019 · arXiv (Cornell University)

The transformer-based pre-trained language model BERT has helped to improve state-of-the-art performance on many natural language processing (NLP) tasks. Using the same architecture and parameters, we developed and evaluated a monolingual Dutch BERT model called …