System and method for learning latent representations for natural language tasks
First Claim
1. A method comprising:
- analyzing a first natural language corpus to generate a latent representation for words in the first natural language corpus;
calculating, for each word in the latent representation, a Euclidian distance between a left context of the each word and a right context of the each word, to yield a centroid of latent vectors for each word in the latent representation;
analyzing a second natural language corpus having a target word, the target word being a word that is not in the first natural language corpus; and
predicting, via a processor, a label for the target word based on the latent representation and the centroid of latent vectors for each word in the latent representation.
3 Assignments
0 Petitions
Accused Products
Abstract
Disclosed herein are systems, methods, and non-transitory computer-readable storage media for learning latent representations for natural language tasks. A system configured to practice the method analyzes, for a first natural language processing task, a first natural language corpus to generate a latent representation for words in the first corpus. Then the system analyzes, for a second natural language processing task, a second natural language corpus having a target word, and predicts a label for the target word based on the latent representation. In one variation, the target word is one or more word such as a rare word and/or a word not encountered in the first natural language corpus. The system can optionally assigning the label to the target word. The system can operate according to a connectionist model that includes a learnable linear mapping that maps each word in the first corpus to a low dimensional latent space.
173 Citations
20 Claims
-
1. A method comprising:
-
analyzing a first natural language corpus to generate a latent representation for words in the first natural language corpus; calculating, for each word in the latent representation, a Euclidian distance between a left context of the each word and a right context of the each word, to yield a centroid of latent vectors for each word in the latent representation; analyzing a second natural language corpus having a target word, the target word being a word that is not in the first natural language corpus; and predicting, via a processor, a label for the target word based on the latent representation and the centroid of latent vectors for each word in the latent representation. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A system comprising:
-
a processor; and a computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising; analyzing a first natural language corpus to generate a latent representation for words in the first natural language corpus; calculating, for each word in the latent representation, a Euclidian distance between a left context of the each word and a right context of the each word, to yield a centroid of latent vectors for each word in the latent representation; analyzing a second natural language corpus having a target word, the target word being a word that is not in the first natural language corpus; and predicting a label for the target word based on the latent representation and the centroid of latent vectors for each word in the latent representation. - View Dependent Claims (10, 11, 12, 13, 14, 15, 16)
-
-
17. A computer-readable storage device having instructions stored which, when executed by a computing device, cause the computing device to perform operations comprising:
-
analyzing a first natural language corpus to generate a latent representation for words in the first natural language corpus; calculating, for each word in the latent representation, a Euclidian distance between a left context of the each word and a right context of the each word, to yield a centroid of latent vectors for each word in the latent representation; analyzing a second natural language corpus having a target word, the target word being a word that is not in the first natural language corpus; and predicting a label for the target word based on the latent representation and the centroid of latent vectors for each word in the latent representation. - View Dependent Claims (18, 19, 20)
-
Specification