摘要:
Disclosed herein are systems, methods, and non-transitory computer-readable storage media for predicting probabilities of words for a language model. An exemplary system configured to practice the method receives a sequence of words and external data associated with the sequence of words and maps the sequence of words to an X-dimensional vector, corresponding to a vocabulary size. Then the system processes each X-dimensional vector, based on the external data, to generate respective Y-dimensional vectors, wherein each Y-dimensional vector represents a dense continuous space, and outputs at least one next word predicted to follow the sequence of words based on the respective Y-dimensional vectors. The X-dimensional vector, which is a binary sparse representation, can be higher dimensional than the Y-dimensional vector, which is a dense continuous space. The external data can include part-of-speech tags, topic information, word similarity, word relationships, a particular topic, and succeeding parts of speech in a given history.
摘要:
Disclosed herein are systems, methods, and non-transitory computer-readable storage media for predicting probabilities of words for a language model. An exemplary system configured to practice the method receives a sequence of words and external data associated with the sequence of words and maps the sequence of words to an X-dimensional vector, corresponding to a vocabulary size. Then the system processes each X-dimensional vector, based on the external data, to generate respective Y-dimensional vectors, wherein each Y-dimensional vector represents a dense continuous space, and outputs at least one next word predicted to follow the sequence of words based on the respective Y-dimensional vectors. The X-dimensional vector, which is a binary sparse representation, can be higher dimensional than the Y-dimensional vector, which is a dense continuous space. The external data can include part-of-speech tags, topic information, word similarity, word relationships, a particular topic, and succeeding parts of speech in a given history.
摘要:
Methods, systems, and products adapt recommender systems with pairwise feedback. A pairwise question is posed to a user. A response is received that selects a preference for a pair of items in the pairwise question. A latent factor model is adapted to incorporate the response, and an item is recommended to the user based on the response.
摘要:
Methods, systems, and products adapt recommender systems with pairwise feedback. A pairwise question is posed to a user. A response is received that selects a preference for a pair of items in the pairwise question. A latent factor model is adapted to incorporate the response, and an item is recommended to the user based on the response.
摘要:
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.
摘要:
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.
摘要:
A memory array contains a plurality of banks coupled to each other by a plurality of data lines. Each of the data lines is divided into a plurality of segments within the array. Respective bidirectional buffers couple read data from one of the segments to another in a first direction, and to couple write data from one of the segments to another in a second direction that is opposite the first direction. The data lines may be local data read/write lines that couple different banks of memory cells to each other and to respective data terminals, digit lines that couple memory cells in a respective column to respective sense amplifiers, word lines that activate memory cells in a respective row, or some other signal line within the array. The memory array also includes precharge circuits for precharging the segments of respective data lines to a precharge voltage.
摘要:
A memory array contains a plurality of banks coupled to each other by a plurality of data lines. Each of the data lines is divided into a plurality of segments within the array. Respective bidirectional buffers couple read data from one of the segments to another in a first direction, and to couple write data from one of the segments to another in a second direction that is opposite the first direction. The data lines may be local data read/write lines that couple different banks of memory cells to each other and to respective data terminals, digit lines that couple memory cells in a respective column to respective sense amplifiers, word lines that activate memory cells in a respective row, or some other signal line within the array. The memory array also includes precharge circuits for precharging the segments of respective data lines to a precharge voltage.
摘要:
A memory array contains a plurality of banks coupled to each other by a plurality of data lines. Each of the data lines is divided into a plurality of segments within the array. Respective bidirectional buffers couple read data from one of the segments to another in a first direction, and to couple write data from one of the segments to another in a second direction that is opposite the first direction. The data lines may be local data read/write lines that couple different banks of memory cells to each other and to respective data terminals, digit lines that couple memory cells in a respective column to respective sense amplifiers, word lines that activate memory cells in a respective row, or some other signal line within the array. The memory array also includes precharge circuits for precharging the segments of respective data lines to a precharge voltage.
摘要:
A memory array contains a plurality of banks coupled to each other by a plurality of data lines. Each of the data lines is divided into a plurality of segments within the array. Respective bidirectional buffers couple read data from one of the segments to another in a first direction, and to couple write data from one of the segments to another in a second direction that is opposite the first direction. The data lines may be local data read/write lines that couple different banks of memory cells to each other and to respective data terminals, digit lines that couple memory cells in a respective column to respective sense amplifiers, word lines that activate memory cells in a respective row, or some other signal line within the array. The memory array also includes precharge circuits for precharging the segments of respective data lines to a precharge voltage.