Transforming input sequences to output sequences non-autoregressively using machine learning
AssigneeNVIDIA Corporation
InventorsHainan XU, Boris GINSBURG
Life of this patent
Estimating the term…
Abstract
In various examples, a technique for transforming an input sequence to an output sequence using a machine learning model is disclosed. The technique includes encoding a sequence of inputs in a representation of the sequence of inputs. The technique also includes causing the generation of a sequence of joint probabilities based on the representation of the sequence of inputs and no history of previously predicted output labels. The technique also includes causing the generation of a sequence of output labels based on the sequence of joint probabilities.
Claims20
A method comprising:
- encoding a sequence of inputs into a representation of the sequence of inputs;
- based at least on the representation of the sequence of inputs and without a history of previously predicted output labels, causing the generation of a sequence of joint probabilities, wherein each joint probability of the sequence of joint probabilities is computed based at least on a respective first probability distribution over a set of output labels and a respective second probability distribution over a set of allowed durations;
- and
- causing the generation of a sequence of output labels based at least on the sequence of joint probabilities.
At least one processor comprising:
- one or more circuits to:
- encode a sequence of inputs into a representation of the sequence of inputs;
- based at least on the representation of the sequence of inputs and without a history of previously predicted output labels, cause the generation of a sequence of joint probabilities, wherein individual joint probabilities of the sequence of joint probabilities are computed based at least on a respective first probability distribution over a set of output labels and a respective second probability distribution over a set of allowed durations;
- and
- cause the generation of a sequence of output labels based at least on the sequence of joint probabilities.
A system comprising:
- one or more processing units to execute operations comprising:
- encoding a sequence of inputs into a representation of the sequence of inputs;
- based at least on the representation of the sequence of inputs and without a history of previously predicted output labels, causing generation of a sequence of joint probabilities, wherein individual joint probabilities of the sequence of joint probabilities are computed based at least on a respective first probability distribution over a set of output labels and a respective second probability distribution over a set of allowed durations;
- and
- causing the generation of a sequence of output labels based at least on the sequence of joint probabilities.
Dependencies are inferred from the claim text.