Dialect differences caused by regional, social, and economic factors cause performance discrepancies for many groups of language technology users. Inclusive and equitable language technology must critically be dialect invariant, meaning that performance remains constant over dialectal shifts. Current systems often fall short of this ideal since they are designed and tested on a single dialect: Standard American English (SAE). We introduce a suite of resources for evaluating and achieving English dialect invariance. The resource is called Multi-VALUE, a controllable rule-based translation system spanning 50 English dialects and 189 unique linguistic features. Multi-VALUE maps SAE to synthetic forms of each dialect. First, we use this system to stress tests question answering, machine translation, and semantic parsing. Stress tests reveal significant performance disparities for leading models on non-standard dialects. Second, we use this system as a data augmentation technique to improve the dialect robustness of existing systems. Finally, we partner with native speakers of Chicano and Indian English to release new gold-standard variants of the popular CoQA task. To execute the transformation code, run model checkpoints, and download both synthetic and gold-standard dialectal benchmark datasets, see http://value-nlp.org.

From the approachable Geordie dialect to the instantly recognisable Liverpool lilt, many of England's most distinctive accents are from the north. But a new study has warned that northern accents could all but disappear in just 45 years. Using physics modelling, researchers from the Universities of Portsmouth and Cambridge predicted how accents are likely to change across England by 2066. Their findings suggest that northern accents could be replaced with'posh' south eastern pronunciations. However, certain north-south differences are predicted to remain - we will continue to disagree about the pronunciation of bath', according to the researchers.

This podcast also looks at some exciting developments in astronomy that have happened over the past week; and we find out why machine learning …