Inflectional variation is a common feature of World Englishes such as Colloquial Singapore English and African American Vernacular English. Although comprehension by human readers is usually unimpaired by non-standard inflections, currenl NLP systems are not yet robust. We propose Base-Inflection Encoding (BITE), a method to tokenize English text by reducing inllected words to their base forms before reinjecting the grammatical information as special symbols. Fine-tuning pre-trained NLP models for downstream tasks using our encoding defends against inflectional adversaries while maintaining performance on clean data. Models using BITE generalize better to dialects with non-standard inflections without explicit training and translation models converge faster when trained with BITE. Finally, we show that our encoding improves the vocabulary efficiency of popular data-driven subword tokenizers. Since there has been no prior work on quantitatively evaluating vocabulary efficiency, we propose metrics to do so.
展开▼
