Teaching syntax by adversarial distraction
AssigneeNEC Laboratories America, Inc.
InventorsChristopher Malon, Asim Kadav, Juho Kim
Life of this patent
Estimating the term…
Abstract
A computer-implemented method and system are provided for teaching syntax for training a neural network based natural language inference model. The method includes selectively performing, by the hardware processor, person reversal on a set of hypothesis sentences, based on person reversal prevention criteria, to obtain a first training data set. The method further includes enhancing, by the hardware processor, a robustness of the neural network based natural language inference model to syntax changes by training the neural network based natural language inference model on original training data combined with the first data set.
Claims20
A computer-implemented method for teaching syntax for training a neural network based natural language inference model, comprising:
- selectively performing, by the hardware processor, person reversal on a set of hypothesis sentences, based on person reversal prevention criteria, to obtain a first training data set;
- and
- enhancing, by the hardware processor, a robustness of the neural network based natural language inference model to syntax changes by training the neural network based natural language inference model on original training data combined with the first data set.
A computer program product for teaching syntax for training a neural network based natural language inference model, the computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform a method comprising:
- selectively performing, by the hardware processor, person reversal on a set of hypothesis sentences, based on person reversal prevention criteria, to obtain a first training data set;
- enhancing, by the hardware processor, a robustness of the neural network based natural language inference model to syntax changes by training the neural network based natural language inference model on original training data combined with the first data set.
A computer processing system for teaching syntax for training a neural network based natural language inference model, comprising:
- a memory for storing program code;
- and
- a processor for running the program code to:
- selectively perform person reversal on a set of hypothesis sentences, based on person reversal prevention criteria, to obtain a first training data set;
- enhance a robustness of the neural network based natural language inference model to syntax changes by training the neural network based natural language inference model on original training data combined with the first data set.
Dependencies are inferred from the claim text.