We introduce whatlies, an open source toolkit for visually inspecting word and sentence embeddings. The project offers a unified and extensible API with current support for a range of popular embedding backends including spaCy, tfhub, huggingface transformers, gensim, fastText and BytePair embeddings. The package combines a domain specific language for vector arithmetic with visualisation tools that make exploring word embeddings more intuitive and concise. It offers support for many popular dimensionality reduction techniques as well as many interactive visualisations that can either be statically exported or shared via Jupyter notebooks. The project documentation is available from https://rasahq.github.io/whatlies/.

Human listeners are able to quickly and robustly adapt to new accents and do so by using information about speaker’s identities. This paper will present experimental evidence that, even considering information about speaker’s identities, listeners retain a strong bias towards the acoustics of their own dialect after dialect learning. Participants’ behaviour was accurately mimicked by a classifier which was trained on more cases from the base dialect and fewer from the target dialect. This suggests that imbalanced training data may result in automatic speech recognition errors consistent with those of speakers from populations over-represented in the training data.

This project evaluates the accuracy of YouTube’s automatically-generated captions across two genders and five dialect groups. Speakers’ dialect and gender was controlled for by using videos uploaded as part of the “accent tag challenge”, where speakers explicitly identify their language background. The results show robust differences in accuracy across both gender and dialect, with lower accuracy for 1) women and 2) speakers from Scotland. This finding builds on earlier research finding that speaker’s sociolinguistic identity may negatively impact their ability to use automatic speech recognition, and demonstrates the need for sociolinguistically-stratified validation of systems.

Previous work on classifying Twitter users’ political alignment has mainly focused on lexical and social network features. This study provides evidence that political affiliation is also reflected in features which have been previously overlooked: users’ discourse patterns (proportion of Tweets that are retweets or replies) and their rate of use of capitalization and punctuation. We find robust differences between politically left- and right-leaning communities with respect to these discourse and sub-lexical features, although they are not enough to train a high-accuracy classifier.