Systems and methods for neural language modeling
In some aspects, the present disclosure relates to neural language modeling. In one embodiment, a computer-implemented neural network includes a plurality of neural nodes, where each of the neural nodes has a plurality of input weights corresponding to a vector of real numbers. The neural network also includes an input neural node corresponding to a linguistic unit selected from an ordered list of a plurality of linguistic units, and an embedding layer with a plurality of embedding node partitions. Each embedding node partition includes one or more neural nodes. Each of the embedding node partitions corresponds to a position in the ordered list relative to a focus term, is configured to receive an input from an input node, and is configured to generate an output. The neural network also includes a classifier layer with a plurality of neural nodes, each configured to receive the embedding outputs from the embedding layer, and configured to generate an output corresponding to a probability that a particular linguistic unit is the focus term.
1. computer-implemented neural network, comprising:
a plurality of input neural nodes receiving input comprising an ordered list of a plurality of linguistic units with a linguistic unit omitted, each input neural node of the plurality of input neural nodes corresponding to a linguistic unit selected from the ordered list of a plurality of linguistic units, and wherein the input received by the input neural nodes is one-hot encoded;
an embedding layer comprising a plurality of embedding node partitions, wherein each of the embedding node partitions corresponds to a position in the ordered list relative to a focus term and comprises a plurality of neural nodes, wherein the focus term is an omitted linguistic unit from the ordered list of the plurality of linguistic units, the plurality of neural nodes of each of the embedding node partitions receiving an input from a separate set of the input neural nodes and generating an output by at least multiplying the input from each input neural node by one of a plurality of input weights; and
a classifier layer comprising a plurality of neural nodes, each neural node in the classifier layer configured to receive the output from each of the neural nodes of the embedding layer, to generate an output by at least multiplying the output from each neural node of the embedding layer by one of a plurality of input weights, and wherein the output corresponds to a probability that a particular linguistic unit is the focus term;
wherein the input weights for each neural node of a partition of the embedding layer are trained independently of other partitions.
2. The computer-implemented neural network of claim 1 , wherein the linguistic unit is a character.
3. The computer-implemented neural network of claim 1 , wherein the linguistic unit is a word.
4. The computer-implemented neural network of claim 1 , wherein the positions relative to a focus term of the embedding node partitions are window positions relative to the focus term.
5. The computer-implemented neural network of claim 1 , wherein the positions relative to a focus term of the embedding node partitions are directions relative to the focus term.
6. The computer-implemented neural network of claim 1 , wherein the neural network is trained by performing functions that comprise:
removing the focus term from the ordered list of linguistic units;
selecting a partition from each remaining linguistic unit's embeddings based on that linguistic unit's position relative to the focus term;
concatenating the partitions;
propagating the partitions through the classifier layer; and
updating weights for one or more neural nodes in the classifier layer and embedding layer based on accuracy of the classifier layer in predicting that the particular linguistic unit is the focus term.
7. The computer-implemented neural network of claim 1 , wherein the neural network is trained by performing functions that comprise:
training a first partition of the embedding node partitions by:
removing the focus term from the ordered list of linguistic units;
selecting a partition from each remaining linguistic unit's embeddings based on that respective linguistic unit's position relative to the focus term; and
updating weights for each neural node in the classifier layer and embedding layer based on accuracy of the classifier layer in predicting that the particular linguistic unit is the focus term.
8. The computer-implemented neural network of claim 7 , wherein the neural network is trained by performing functions that further comprise:
training a second partition by:
removing the focus term from the ordered list of linguistic units;
selecting a partition from each remaining linguistic unit's embedding based on that linguistic unit's position relative to the focus term; and
updating the weights based on accuracy of the classifier layer in predicting that the particular linguistic unit is the focus term,
wherein the steps of training a first partition and training a second partition are performed in parallel.
9. The computer-implemented neural network of claim 1 , wherein particular linguistic units are selected from the ordered list of the plurality of linguistic units and multiple linguistic domains associated with the selected particular linguistic units are modeled into a common vector space, wherein each of the multiple linguistic domains corresponds to a different language.
10. A system having one or more processors configured to implement:
a plurality of input neural nodes receiving input comprising an ordered list of a plurality of linguistic units with a linguistic unit omitted, each input neural node of the plurality of input neural nodes corresponding to a linguistic unit selected from the ordered list of a plurality of linguistic units, and wherein the input received by the input neural nodes is one-hot encoded;
an embedding layer comprising a plurality of embedding node partitions, wherein each of the embedding node partitions corresponds to a position in the ordered list relative to a focus term and comprises a plurality of neural nodes, wherein the focus term is an omitted linguistic unit from the ordered list of the plurality of linguistic units, the plurality of neural nodes of each of the embedding node partitions receiving an input from a separate set of the input neural nodes and calculating an output by at least multiplying the input from each input by one of a plurality of input weights; and
a classifier layer comprising a plurality of neural nodes, each neural node in the classifier layer configured to receive the output from each of the neural nodes of the embedding layer, to generate an output by at least multiplying the output from each neural node of the embedding layer by one of a plurality of input weights, and wherein the output corresponds to a probability that a particular linguistic unit is the focus term;
wherein the input weights for each neural node of a partition of the embedding layer are trained independently of other partitions.
11. The system of claim 10 , wherein the linguistic unit is a character or a word.
12. The system of claim 10 , wherein the positions relative to a focus term of the embedding node partitions are window positions relative to the focus term or directions relative to the focus term.
13. The system of claim 10 , wherein the plurality of neural nodes, input neural node, embedding layer, and classifier layer form a neural network, the neural network trained by performing functions that comprise:
training a first partition of the embedding node partitions by:
removing the focus term from the ordered list of linguistic units;
selecting a partition from each remaining linguistic unit's embeddings based on that respective linguistic unit's position relative to the focus term; and
updating weights for each neural node in the classifier layer and embedding layer based on accuracy of the classifier layer in predicting that the particular linguistic unit is the focus term.
14. The system of claim 13 , wherein the neural network is trained by performing functions that further comprise:
training a second partition by:
removing the focus term from the ordered list of linguistic units;
selecting a partition from each remaining linguistic unit's embedding based on that linguistic unit's position relative to the focus term; and
updating the weights based on accuracy of the classifier layer in predicting that the particular linguistic unit is the focus term,
wherein the steps of training a first partition and training a second partition are performed in parallel.
15. The system of claim 10 , wherein particular linguistic units are selected from the ordered list of the plurality of linguistic units and multiple linguistic domains associated with the selected particular linguistic units are modeled into a common vector space, wherein each of the multiple linguistic domains corresponds to a different language.