Standard autoregressive language models perform only polynomial-time computation to compute the probability of the next symbol.
We introduce neural finite state transducers (NFSTs), a family of string transduction models defining joint and conditional probability distributions over pairs of strings.
Emails in the workplace are often intentional calls to action for its recipients.
Unsupervised word embeddings have been shown to be valuable as features in supervised learning problems; however, their role in unsupervised problems has been less thoroughly explored.
However, people who are capable of using more than one language often communicate using multiple languages at the same time.