Abstract: Techniques for using logit values for classifying utterances and messages input to chatbot systems in natural language processing. A method can include a chatbot system receiving an utterance generated by a user interacting with the chatbot system. The chatbot system can input the utterance into a machine-learning model including a set of binary classifiers. Each binary classifier of the set of binary classifiers can be associated with a modified logit function. The method can also include the machine-learning model using the modified logit function to generate a set of distance-based logit values for the utterance. The method can also include the machine-learning model applying an enhanced activation function to the set of distance-based logit values to generate a predicted output. The method can also include the chatbot system classifying, based on the predicted output, the utterance as being associated with the particular class.

Abstract: Devices and techniques are disclosed herein to provide a number of different bias signals to each of multiple signal lines of an array of memory cells, each bias signal having an overdrive voltage above a target voltage by a selected increment and an overdrive period, to determine settling times of each of the multiple signal lines to the target voltage for the number of different bias signals, to determine a functional compensation profile for an array of memory cells comprising a relationship between the different bias signals and the determined settling times of the multiple signal lines.

Abstract: Techniques are disclosed herein for adaptive training data augmentation to facilitate training named entity recognition (NER) models. Adaptive augmentation techniques are disclosed herein that take into consideration the distribution of different entity types within training data. The adaptive augmentation techniques generate adaptive numbers of augmented examples (e.g., utterances) based on the distribution of entities to make sure enough numbers of examples for minority class entities are generated during augmentation of the training data.

Abstract: Techniques are disclosed herein for using named entity recognition to resolve entity expression while transforming natural language to a meaning representation language. In one aspect, a method includes accessing natural language text, predicting, by a first machine learning model, a class label for a token in the natural language text, predicting, by a second machine-learning model, operators for a meaning representation language and a value or value span for each attribute of the operators, in response to determining that the value or value span for a particular attribute matches the class label, converting a portion of the natural language text for the value or value span into a resolved format, and outputting syntax for the meaning representation language. The syntax comprises the operators with the portion of the natural language text for the value or value span in the resolved format.

Abstract: Systems and methods fine-tune a pretrained machine learning model. For a model having multiple layers, an initial set of configurations is identified, each configuration establishing layers to be frozen and layers to be fine-tuned. A configuration that is optimized with respect to one or more parameters is selected, establishing a set of fine-tuning layers and a set of frozen layers. An input for the model is provided to a remote system. An output of the set of frozen layers of the model, given the provided input, is received back and locally stored. The set of fine-tuning layers of the model is loaded from the remote system. The model is fine-tuned by retrieving the locally stored output of the set of frozen layers, and updating weights associated with the set of fine-tuning layers of the machine learning model.

Abstract: An augmentation and feature caching subsystem is described for training AI/ML models. In one particular aspect, a method is provided that includes receiving data comprising training examples, one or more augmentation configuration hyperparameters and one or more feature extraction configuration hyperparameters; generating a first key based on one of the training examples and the one or more augmentation configuration hyperparameters; searching a first key-value storage based on the first key; obtaining one or more augmentations based on the search of the first key-value storage; applying the obtained one or more augmentations to the training examples to result in augmented training examples; generating a second key based on one of the augmented training examples and the one or more feature extraction configuration hyperparameters; searching a second key-value storage based on the second key; obtaining one or more features based on the search of the second key-value storage.

Abstract: Techniques are provided for augmenting training data using gazetteers and perturbations to facilitate training named entity recognition models. The training data can be augmented by generating additional utterances from original utterances in the training data and combining the generated additional utterances with the original utterances to form the augmented training data. The additional utterances can be generated by replacing the named entities in the original utterances with different named entities and/or perturbed versions of the named entities in the original utterances selected from a gazetteer. Gazetteers of named entities can be generated from the training data and expanded by searching a knowledge base and/or perturbing the named entities therein. The named entity recognition model can be trained using the augmented training data.

Abstract: Techniques are provided for improved training of a machine learning model using lexical dropout. A machine learning model and a training data set are accessed. The training data set can include sample utterances and corresponding labels. A dropout parameter is identified. The dropout parameter can indicate a likelihood for dropping out one or more feature vectors for tokens associated with respective entities during training of the machine learning model. The dropout parameter is applied to feature vectors for tokens associated with respective entities. The machine learning model is trained using the training data set and the dropout parameter to generate a trained machine learning model. The use of the trained the machine learning model is facilitated.

Abstract: Techniques are provided for improved training of a machine-learning model that includes multiple layers and is configured to process textual language input. The machine-learning model includes one or more blocks in which each block includes a multi-head self-attention network, a first connection for providing input to the multi-head self-attention network, and a second (residual) connection for providing the input to a normalization layer, bypassing the multi-head self-attention network. During training, the second connection is dropped out according to a dropout parameter. Additionally, or alternatively, an attention weight matrix is used for dropout by blocking diagonal entries in the attention weight matrix. As a result, the machine-learning model increasingly focuses on contextual information, which provides more accurate language processing results.

Abstract: Techniques disclosed herein relate generally to language detection. In one particular aspect, a method is provided that includes obtaining a sequence of n-grams of a textual unit; using an embedding layer to obtain an ordered plurality of embedding vectors for the sequence of n-grams; using a deep network to obtain an encoded vector that is based on the ordered plurality of embedding vectors; and using a classifier to obtain a language prediction for the textual unit that is based on the encoded vector. The deep network includes an attention mechanism, and using the embedding layer to obtain the ordered plurality of embedding vectors comprises, for each n-gram in the sequence of n-grams: obtaining hash values for the n-gram; based on the hash values, selecting component vectors from among the plurality of component vectors; and obtaining an embedding vector for the n-gram that is based on the component vectors.

Abstract: In some aspects, a computer obtains a trained conditional random field (CRF) model comprising a set of model parameters learned from training data and stored in a transition matrix. Tag sequences, inconsistent with the tag sequence logic, are identified for the tags within the transition matrix. setting, within the transition matrix, a cost associated with transitioning between the pair of tags to be equal to a predefined hyperparameter value that penalizes the transitioning between the inconsistent pair of tags. The CRF model receives a string of text comprising one or more named entities. The CRF model inputs the string of text into the CRF model having the cost associated with the transitioning between the pair of tags set equal to the predefined hyperparameter value. The CRF model classifies the words within the string of text into different classes which might include the one or more named entities.

Abstract: Techniques are provided for customizing or fine-tuning a pre-trained version of a machine-learning model that includes multiple layers and is configured to process audio or textual language input. Each of the multiple layers is configured with a plurality of layer-specific pre-trained parameter values corresponding to a plurality of parameters, and each of the multiple layers is configured to implement multi-head attention. An incomplete subset of the multiple layers is identified for which corresponding layer-specific pre-trained parameter values are to be fine-tuned using a client data set. The machine-learning model is fine-tuned using the client data set to generate an updated version of the machine-learning model, where the layer-specific pre-trained parameter values configured for each layer of one of more of the multiple layers not included in the incomplete subset are frozen during the fine-tuning. Use of the updated version of the machine-learning model is facilitated.

Abstract: Techniques are disclosed herein for focused training of language models and end-to-end hypertuning of the framework. In one aspect, a method is provided that includes obtaining a machine learning model pre-trained for language modeling, and post-training the machine learning model for various tasks to generate a focused machine learning model. The post-training includes: (i) training the machine learning model on an unlabeled set of training data pertaining to a task that the machine learning model was pre-trained for as part of the language modeling, and the unlabeled set of training data is obtained with respect to a target domain, a target task, or a target language, and (ii) training the machine learning model on a labeled set of training data that pertains to another task that is an auxiliary task related to a downstream task to be performed using the machine learning model or output from the machine learning model.

Abstract: A device includes a memory array and a sense circuit coupled with the memory array. The sense circuit includes a sense node coupled with a data line of the memory array. A first sensing path includes a first transistor having a first gate coupled with the sense node. A second sensing path includes a second transistor having a second gate coupled with the sense node. A first threshold voltage of the first transistors differs from a second threshold voltage of the second transistor by a threshold voltage gap.

Abstract: A device includes a memory array and a sense circuit coupled with the memory array. The sense circuit includes a sense node coupled with a data line of the memory array. A first sensing path includes a first transistor having a first gate coupled with the sense node. A second sensing path includes a second transistor having a second gate coupled with the sense node. A first threshold voltage of the first transistors differs from a second threshold voltage of the second transistor by a threshold voltage gap.

Abstract: Techniques for using logit values for classifying utterances and messages input to chatbot systems in natural language processing. A method can include a chatbot system receiving an utterance generated by a user interacting with the chatbot system. The chatbot system can input the utterance into a machine-learning model including a set of binary classifiers. Each binary classifier of the set of binary classifiers can be associated with a modified logit function. The method can also include the machine-learning model using the modified logit function to generate a set of distance-based logit values for the utterance. The method can also include the machine-learning model applying an enhanced activation function to the set of distance-based logit values to generate a predicted output. The method can also include the chatbot system classifying, based on the predicted output, the utterance as being associated with the particular class.

Abstract: Disclosed herein are techniques for addressing an overconfidence problem associated with machine learning models in chatbot systems. For each layer of a plurality of layers of a machine learning model, a distribution of confidence scores is generated for a plurality of predictions with respect to an input utterance. A prediction is determined for each layer of the machine learning model based on the distribution of confidence scores generated for the layer. Based on the predictions, an overall prediction of the machine learning model is determined. A subset of the plurality of layers are iteratively processed to identify a layer whose assigned prediction satisfies a criterion. A confidence score associated with the assigned prediction of the layer of the machine learning model is assigned as an overall confidence score to be associated with the overall prediction of the machine learning model.

Abstract: Techniques for using enhanced logit values for classifying utterances and messages input to chatbot systems in natural language processing. A method can include a chatbot system receiving an utterance generated by a user interacting with the chatbot system and inputting the utterance into a machine-learning model including a series of network layers. A final network layer of the series of network layers can include a logit function. The machine-learning model can map a first probability for a resolvable class to a first logit value using the logit function. The machine-learning model can map a second probability for a unresolvable class to an enhanced logit value. The method can also include the chatbot system classifying the utterance as the resolvable class or the unresolvable class based on the first logit value and the enhanced logit value.

Abstract: Devices and techniques are disclosed herein to provide a number of different bias signals to each of multiple signal lines of an array of memory cells, each bias signal having an overdrive voltage above a target voltage by a selected increment and an overdrive period, to determine settling times of each of the multiple signal lines to the target voltage for the number of different bias signals, to determine a functional compensation profile for an array of memory cells comprising a relationship between the different bias signals and the determined settling times of the multiple signal lines.

Abstract: Devices and techniques are disclosed herein to compensate for variance in one or more electrical parameters across multiple signal lines of an array of memory cells. A compensation circuit can provide a bias signal to a first one of the multiple signal lines, the bias signal having an overdrive voltage greater than a target voltage by a selected increment for a selected overdrive period.