Двунаправленный описывает модель или систему, использующую контекст как до, так и после целевого элемента при его интерпретации или прогнозировании. В языковых моделях двунаправленная обработка может улучшать понимание, поскольку модель учитывает окружающий текст по обе стороны слова или токена.
A term used to describe a system that evaluates the text that both precedes and follows a target section of text. In contrast, a unidirectional system only evaluates the text that precedes a target section of text. For example, consider a masked language model that must determine probabilities for the word or words representing the underline in the following question: What is the _____ with you? A unidirectional language model would have to base its probabilities only on the context provided by the words "What", "is", and "the". In contrast, a bidirectional language model could also gain context from "with" and "you", which might help the model generate better predictions.