Abstract: Systems described herein may use transformer-based machine classifiers to perform a variety of natural language understanding tasks including, but not limited to sentence classification, named entity recognition, sentence similarity, and question answering. The exceptional performance of transformer-based language models is due to their ability to capture long-term temporal dependencies in input sequences. Machine classifiers may be trained using training data sets for multiple tasks, such as but not limited to sentence classification tasks and sequence labeling tasks. Loss masking may be employed in the machine classifier to jointly train the machine classifier on multiple tasks simultaneously. The user of transformer encoders in the machine classifiers, which treat each output sequence independently of other output sequences, in accordance with aspects of the invention do not require joint labeling to model tasks.

Abstract: In a variety of embodiments, machine classifiers may model multi-turn dialogue as a one-to-many prediction task. The machine classifier may be trained using adversarial bootstrapping between a generator and a discriminator with multi-turn capabilities. The machine classifiers may be trained in both auto-regressive and traditional teacher-forcing modes, with the generator including a hierarchical recurrent encoder-decoder network and the discriminator including a bi-directional recurrent neural network. The discriminator input may include a mixture of ground truth labels, the teacher-forcing outputs of the generator, and/or noise data. This mixture of input data may allow for richer feedback on the autoregressive outputs of the generator. The outputs can be ranked based on the discriminator feedback and a response selected from the ranked outputs.

Abstract: In a variety of embodiments, machine classifiers may model multi-turn dialogue as a one-to-many prediction task. The machine classifier may be trained using adversarial bootstrapping between a generator and a discriminator with multi-turn capabilities. The machine classifiers may be trained in both auto-regressive and traditional teacher-forcing modes, with the generator including a hierarchical recurrent encoder-decoder network and the discriminator including a bi-directional recurrent neural network. The discriminator input may include a mixture of ground truth labels, the teacher-forcing outputs of the generator, and/or noise data. This mixture of input data may allow for richer feedback on the autoregressive outputs of the generator. The outputs can be ranked based on the discriminator feedback and a response selected from the ranked outputs.

Abstract: Systems described herein may use transformer-based machine classifiers to perform a variety of natural language understanding tasks including, but not limited to sentence classification, named entity recognition, sentence similarity, and question answering. The exceptional performance of transformer-based language models is due to their ability to capture long-term temporal dependencies in input sequences. Machine classifiers may be trained using training data sets for multiple tasks, such as but not limited to sentence classification tasks and sequence labeling tasks. Loss masking may be employed in the machine classifier to jointly train the machine classifier on multiple tasks simultaneously. The user of transformer encoders in the machine classifiers, which treat each output sequence independently of other output sequences, in accordance with aspects of the invention do not require joint labeling to model tasks.

Abstract: Systems and methods for generating responses to user input such as dialogues, and images are discussed. The system may generate, by a response generation module of at least one server, an optimal generated response to the user communication by applying an generative adversarial network. In some embodiments, the generative adversarial network may include a hierarchical recurrent encoder decoder generative adversarial network including a generator and a discriminator component.

Abstract: By way of example, the technology disclosed by this document may be implemented in a method that includes receiving stored sensor data describing characteristics of a vehicle in motion at a past time and extracting features for prediction and features for recognition from the stored sensor data. The features for prediction may be input into a prediction network, which may generate a predicted label for a past driver action based on the features for prediction. The features for recognition may be input into a recognition network, which may generate a recognized label for the past driver action based on the features for recognition. In some instances, the method may include training prediction network weights of the prediction network using the recognized label and the predicted label.

Abstract: Aspects described herein may allow for the application of stochastic gradient boosting techniques to the training of deep neural networks by disallowing gradient back propagation from examples that are correctly classified by the neural network model while still keeping correctly classified examples in the gradient averaging. Removing the gradient contribution from correctly classified examples may regularize the deep neural network and prevent the model from overfitting. Further aspects described herein may provide for scheduled boosting during the training of the deep neural network model conditioned on a mini-batch accuracy and/or a number of training iterations. The model training process may start un-boosted, using maximum likelihood objectives or another first loss function.

Abstract: Various embodiments may be generally directed to the use of an adversarial learning framework for persona-based dialogue modeling. In some embodiments, automated multi-turn dialogue response generation may be performed using a persona-based hierarchical recurrent encoder-decoder-based generative adversarial network (phredGAN). Such a phredGAN may feature a persona-based hierarchical recurrent encoder-decoder (PHRED) generator and a conditional discriminator. In some embodiments, the conditional discriminator may include an adversarial discriminator that is provided with attribute representations as inputs. In some other embodiments, the conditional discriminator may include an attribute discriminator, and attribute representations may be handled as targets of the attribute discriminator. The embodiments are not limited in this context.

Abstract: Systems and methods for generating responses to user input such as dialogues, and images are discussed. The system may generate, by a response generation module of at least one server, an optimal generated response to the user communication by applying an generative adversarial network. In some embodiments, the generative adversarial network may include a hierarchical recurrent encoder decoder generative adversarial network including a generator and a discriminator component.

Abstract: Aspects described herein may allow for the application of stochastic gradient boosting techniques to the training of deep neural networks by disallowing gradient back propagation from examples that are correctly classified by the neural network model while still keeping correctly classified examples in the gradient averaging. Removing the gradient contribution from correctly classified examples may regularize the deep neural network and prevent the model from overfitting. Further aspects described herein may provide for scheduled boosting during the training of the deep neural network model conditioned on a mini-batch accuracy and/or a number of training iterations. The model training process may start un-boosted, using maximum likelihood objectives or another first loss function.

Abstract: Various embodiments may be generally directed to the use of an adversarial learning framework for persona-based dialogue modeling. In some embodiments, automated multi-turn dialogue response generation may be performed using a persona-based hierarchical recurrent encoder-decoder-based generative adversarial network (phredGAN). Such a phredGAN may feature a persona-based hierarchical recurrent encoder-decoder (PHRED) generator and a conditional discriminator. In some embodiments, the conditional discriminator may include an adversarial discriminator that is provided with attribute representations as inputs. In some other embodiments, the conditional discriminator may include an attribute discriminator, and attribute representations may be handled as targets of the attribute discriminator. The embodiments are not limited in this context.

Abstract: Machine classifiers in accordance with embodiments of the invention capture long-term temporal dependencies in the dialogue data better than the existing recurrent neural network-based architectures. Additionally, machine classifiers may model the joint distribution of the context and response as opposed to the conditional distribution of the response given the context as employed in sequence-to-sequence frameworks. Further, input data may be bidirectionally encoded using both forward and backward separators. The forward and backward representations of the input data may be used to train the machine classifiers using a single generative model and/or shared parameters between the encoder and decoder of the machine classifier. During inference, the backward model may be used to reevaluate previously generated output sequences and the forward model may be used to generate an output sequence based on the previously generated output sequences.

Abstract: Machine classifiers in accordance with embodiments of the invention capture long-term temporal dependencies in particular tasks, such as turn-based dialogues. Machine classifiers may be used to help users to perform tasks indicated by the user. When a user utterance is received, natural language processing techniques may be used to understand the user's intent. Templates may be determined based on the user's intent in the generation of responses to solicit information from the user. A variety of persona attributes may be determined for a user. The persona attributes may be determined based on the user's utterances and/or provided as metadata included with the user's utterances. A response persona may be used to generate responses to the user's utterances such that the generated responses match a tone appropriate to the task. A response persona may be used to generate templates to solicit additional information and/or generate responses appropriate to the task.

Abstract: Machine classifiers in accordance with embodiments of the invention capture long-term temporal dependencies in the dialogue data better than the existing RNN-based architectures. Additionally, machine classifiers may model the joint distribution of the context and response as opposed to the conditional distribution of the response given the context as employed in sequence-to-sequence frameworks. Machine classifiers in accordance with embodiments further append random paddings before and/or after the input data to reduce the syntactic redundancy in the input data, thereby improving the performance of the machine classifiers for a variety of dialogue-related tasks. The random padding of the input data may further provide regularization during the training of the machine classifier and/or reduce exposure bias. In a variety of embodiments, the input data may be encoded based on subword tokenization.

Abstract: Machine classifiers in accordance with embodiments of the invention capture long-term temporal dependencies in particular tasks, such as turn-based dialogues. Machine classifiers may be used to help users to perform tasks indicated by the user. When a user utterance is received, natural language processing techniques may be used to understand the user's intent. Templates may be determined based on the user's intent in the generation of responses to solicit information from the user. A variety of persona attributes may be determined for a user. The persona attributes may be determined based on the user's utterances and/or provided as metadata included with the user's utterances. A response persona may be used to generate responses to the user's utterances such that the generated responses match a tone appropriate to the task. A response persona may be used to generate templates to solicit additional information and/or generate responses appropriate to the task.

Abstract: Systems described herein may use machine classifiers to perform a variety of natural language understanding tasks including, but not limited to multi-turn dialogue generation. Machine classifiers in accordance with aspects of the disclosure may model multi-turn dialogue as a one-to-many prediction task. The machine classifier may be trained using adversarial bootstrapping between a generator and a discriminator with multi-turn capabilities. The machine classifiers may be trained in both auto-regressive and traditional teacher-forcing modes, with the maximum likelihood loss of the auto-regressive outputs being weighted by the score from a metric-based discriminator model. The discriminators input may include a mixture of ground truth labels, the teacher-forcing outputs of the generator, and/or negative examples from the dataset. This mixture of input may allow for richer feedback on the autoregressive outputs of the generator.

Abstract: Aspects discussed herein may relate to methods and techniques for embedding constrained and unconstrained optimization programs as layers in a neural network architecture. Systems are provided that implement a method of solving a particular optimization problem by a neural network architecture. Prior systems required use of external software to pre-solve optimization programs so that previously determined parameters could be used as fixed input in the neural network architecture. Aspects described herein may transform the structure of common optimization problems/programs into forms suitable for use in a neural network. This transformation may be invertible, allowing the system to learn the solution to the optimization program using gradient descent techniques via backpropagation of errors through the neural network architecture. Thus these optimization layers may be solved via operation of the neural network itself.

Abstract: Aspects described herein may allow for the application of stochastic gradient boosting techniques to the training of deep neural networks by disallowing gradient back propagation from examples that are correctly classified by the neural network model while still keeping correctly classified examples in the gradient averaging. Removing the gradient contribution from correctly classified examples may regularize the deep neural network and prevent the model from overfitting. Further aspects described herein may provide for scheduled boosting during the training of the deep neural network model conditioned on a mini-batch accuracy and/or a number of training iterations. The model training process may start un-boosted, using maximum likelihood objectives or another first loss function.

Abstract: By way of example, the technology disclosed by this document is capable of receiving signal data from one or more sensors; inputting the signal data into an input layer of a deep neural network (DNN), the DNN including one or more layers; generating, using the one or more layers of the DNN, one or more spatial representations of the signal data; generating, using one or more hierarchical temporal memories (HTMs) respectively associated with the one or more layers of the DNNs, one or more temporal predictions by the DNN based on the one or more spatial representations; and generating an anticipation of a future outcome by recognizing a temporal pattern based on the one or more temporal predictions.

Abstract: Various embodiments may be generally directed to the use of an adversarial learning framework for persona-based dialogue modeling. In some embodiments, automated multi-turn dialogue response generation may be performed using a persona-based hierarchical recurrent encoder-decoder-based generative adversarial network (phredGAN). Such a phredGAN may feature a persona-based hierarchical recurrent encoder-decoder (PHRED) generator and a conditional discriminator. In some embodiments, the conditional discriminator may include an adversarial discriminator that is provided with attribute representations as inputs. In some other embodiments, the conditional discriminator may include an attribute discriminator, and attribute representations may be handled as targets of the attribute discriminator. The embodiments are not limited in this context.