Сжатое Представление

AbstractWe present ReadOnce Transformers, an approach to convert a transformer-based model into one that can build an information-capturing, task-independent, and compressed representation of text. The resulting representation is reusable across …...

AbstractWe identify hard problems for neural machine translation models by analyzing progressively higher-scoring translations generated by letting models cheat to various degrees. If a system cheats and still gets something …...