Abstract: There is included a method and apparatus comprising computer code for instance-wise adaptive knowledge injection in a pre-trained language model (PTLM) including determining a necessity of external knowledge in a plurality of queries of a first dataset based on a likelihood that a respective query is solved by internal knowledge of a target model. Then, the one or more queries determined to need external knowledge may be augmented with pieces of external knowledge. A combined dataset may be generated by combining the first dataset and the one or more augmented queries, and the combined dataset may be applied to the target model.

Abstract: There is included a method and apparatus comprising computer code configured to cause a processor or processors to perform generating one or more aligned inventories, wherein the one or more aligned inventories are generated using one or more word sense inventories, obtaining a word in a context sentence, determining one or more semantic equivalence scores indicating semantic similarity between the word in the context sentence and each of one or more associated glosses in the one or more aligned inventories using a semantic equivalence recognizer model, and predicting a correct sense of the word in the context sentence based on the determined one or more semantic equivalence scores.

Abstract: A method including: receiving an input comprising natural language texts; selecting, via a knowledge selector, one of a plurality of knowledge categories from an external memory based on a context of the input; retrieving one or more helpful knowledge pieces from the selected knowledge category; augmenting the input using the one or more helpful knowledge pieces; feeding the augmented input into a text-to-text model; and generating an output answer based on the text-to-text model.

Abstract: There is included a method and apparatus comprising computer code for instance-wise adaptive knowledge injection in a pre-trained language model (PTLM) including determining a necessity of external knowledge in a plurality of queries of a first dataset based on a likelihood that a respective query is solved by internal knowledge of a target model. Then, the one or more queries determined to need external knowledge may be augmented with pieces of external knowledge. A combined dataset may be generated by combining the first dataset and the one or more augmented queries, and the combined dataset may be applied to the target model.

Abstract: A method performed by at least one processor includes receiving a first input stream of a task and a second input stream of a solution. The method further includes selecting the first input stream or the second input stream. The method further includes providing the selected input stream to an image conversion model and a language model. The method further includes creating, based on the selected input stream, a model ensemble of the conversion model and the language model. The method further includes outputting a prediction based on the model ensemble. The method may further include generating an image corresponding to text, converting a textual task into a multimodal task, and solving the multimodal task.

Abstract: A method including receiving input comprising natural language texts; pre-training a First-Order Logic Network (FOLNet) neural network model on unlabeled texts included in the natural language texts, the FOLNet neural network model comprising of a plurality of layers; processing the input through the plurality of layers of the FOLNet neural network model; encoding a logical inductive bias using the FOLNet neural network model; outputting one or more tensors based on the logical inductive bias; and predicting an outcome using the one or more tensors.

Abstract: There is included a method and apparatus comprising computer code configured to cause a processor or processors to perform generating one or more aligned inventories, wherein the one or more aligned inventories are generated using one or more word sense inventories, obtaining a word in a context sentence, determining one or more semantic equivalence scores indicating semantic similarity between the word in the context sentence and each of one or more associated glosses in the one or more aligned inventories using a semantic equivalence recognizer model, and predicting a correct sense of the word in the context sentence based on the determined one or more semantic equivalence scores.

Abstract: A processing unit can operate a first recurrent computational model (RCM) to provide first state information and a predicted result value. The processing unit can operating a first network computational model (NCM) to provide respective expectation values of a plurality of actions based at least in part on the first state information. The processing unit can provide an indication of at least one of the plurality of actions, and receive a reference result value, e.g., via a communications interface. The processing unit can train the first RCM based at least in part on the predicted result value and the reference result value to provide a second RCM, and can train the first NCM based at least in part on the first state information and the at least one of the plurality of actions to provide a second NCM.

Abstract: A method for generating an automatic speech recognition (ASR) model using unsupervised learning includes obtaining, by a device, text information. The method includes determining, by the device, a set of phoneme sequences associated with the text information. The method includes obtaining, by the device, speech waveform data. The method includes determining, by the device, a set of phoneme boundaries associated with the speech waveform data. The method includes generating, by the device, the ASR model using an output distribution matching (ODM) technique based on determining the set of phoneme sequences associated with the text information and based on determining the set of phoneme boundaries associated with the speech waveform data.

Abstract: A processing unit can determine a first feature value corresponding to a session by operating a first network computational model (NCM) based part on information of the session. The processing unit can determine respective second feature values corresponding to individual actions of a plurality of actions by operating a second NCM. The second NCM can use a common set of parameters in determining the second feature values. The processing unit can determine respective expectation values of some of the actions of the plurality of actions based on the first feature value and the respective second feature values. The processing unit can select a first action of the plurality of actions based on at least one of the expectation values. In some examples, the processing unit can operate an NCM to determine expectation values based on information of a session and information of respective actions.

Abstract: In classification tasks applicable to data that exhibit sequential output statistics, a classifier may be trained in an unsupervised manner based on a sequence of input samples and an unaligned sequence of output labels, using a cost function that measures the negative cross-entropy of an N-gram joint probability distribution derived from the sequence of output labels with respect to an expected N-gram frequency in a second sequence of output labels predicted by the classifier. In some embodiments, a primal-dual reformulation of the cost function is employed to facilitate optimization.

Abstract: A method for generating an automatic speech recognition (ASR) model using unsupervised learning includes obtaining, by a device, text information. The method includes determining, by the device, a set of phoneme sequences associated with the text information. The method includes obtaining, by the device, speech waveform data. The method includes determining, by the device, a set of phoneme boundaries associated with the speech waveform data. The method includes generating, by the device, the ASR model using an output distribution matching (ODM) technique based on determining the set of phoneme sequences associated with the text information and based on determining the set of phoneme boundaries associated with the speech waveform data.

Abstract: Provided are methods and systems for facilitating selection of a cloud configuration for deploying an application program with high accuracy, low overhead, and automatic adaptivity to a broad spectrum of applications and cloud configurations. The methods and systems are designed for building a performance model of cloud configurations, where the performance model is capable of distinguishing an optimal cloud configuration or a near-optimal cloud configuration from other possible configurations, but without requiring the model to be accurate for every cloud configuration. By tolerating the inaccuracy of the model for some configurations (but keeping the accuracy of the final result) it is possible to achieve both low overhead and automatic adaptivity: only a small number of samples may be needed and there is no need to embed application-specific insights into the modeling.

Abstract: A processing unit can acquire datasets from respective data sources, each having a respective unique data domain. The processing unit can determine values of a plurality of features based on the plurality of datasets. The processing unit can modify input-specific parameters or history parameters of a computational model based on the values of the features. In some examples, the processing unit can determine an estimated value of a target feature based at least in part on the modified computational model and values of one or more reference features. In some examples, the computational model can include neural networks for several input sets. An output layer of at least one of the neural networks can be connected to the respective hidden layer(s) of one or more other(s) of the neural networks. In some examples, the neural networks can be operated to provide transformed feature value(s) for respective times.

Abstract: A processing unit can successively operate layers of a multilayer computational graph (MCG) according to a forward computational order to determine a topic value associated with a document based at least in part on content values associated with the document. The processing unit can successively determine, according to a reverse computational order, layer-specific deviation values associated with the layers based at least in part on the topic value, the content values, and a characteristic value associated with the document. The processing unit can determine a model adjustment value based at least in part on the layer-specific deviation values. The processing unit can modify at least one parameter associated with the MCG based at least in part on the model adjustment value. The MCG can be operated to provide a result characteristic value associated with test content values of a test document.

Abstract: Techniques for providing a people recommendation system for predicting and recommending relevant people (or other entities) to include in a conversation based on contextual indicators. In an exemplary embodiment, email recipient recommendations may be suggested based on contextual signals, e.g., project names, body text, existing recipients, current date and time, etc. In an aspect, a plurality of properties including ranked key phrases are associated with profiles corresponding to personal entities. Aggregated profiles are analyzed using first- and second-layer processing techniques. The recommendations may be provided to the user reactively, e.g., in response to a specific query by the user to the people recommendation system, or proactively, e.g., based on the context of what the user is currently working on, in the absence of a specific query by the user.

Abstract: In classification tasks applicable to data that exhibit sequential output statistics, a classifier may be trained in an unsupervised manner based on a sequence of input samples and an unaligned sequence of output labels, using a cost function that measures the negative cross-entropy of an N-gram joint probability distribution derived from the sequence of output labels with respect to an expected N-gram frequency in a second sequence of output labels predicted by the classifier. In some embodiments, a primal-dual reformulation of the cost function is employed to facilitate optimization.

Abstract: Systems, methods, and computer-readable media for providing semantically-relevant discovery of solutions are described herein. In some examples, a computing device can receive an input, such as a query. The computing device can process each word of the input sequentially to determine a semantic representation of the input. Techniques and technologies described herein determine a response to the input, such as an answer, based on the semantic representation of the input matching a semantic representation of the response. An output including one or more relevant responses to the request can then be provided to the requestor. Example techniques described herein can apply machine learning to train a model with click-through data to provide semantically-relevant discovery of solutions. Example techniques described herein can apply recurrent neural networks (RNN) and/or long short term memory (LSTM) cells in the machine learning model.

Abstract: Provided are methods and systems for facilitating selection of a cloud configuration for deploying an application program with high accuracy, low overhead, and automatic adaptivity to a broad spectrum of applications and cloud configurations. The methods and systems are designed for building a performance model of cloud configurations, where the performance model is capable of distinguishing an optimal cloud configuration or a near-optimal cloud configuration from other possible configurations, but without requiring the model to be accurate for every cloud configuration. By tolerating the inaccuracy of the model for some configurations (but keeping the accuracy of the final result) it is possible to achieve both low overhead and automatic adaptivity: only a small number of samples may be needed and there is no need to embed application-specific insights into the modeling.

Abstract: A processing unit can determine a first feature value corresponding to a session by operating a first network computational model (NCM) based part on information of the session. The processing unit can determine respective second feature values corresponding to individual actions of a plurality of actions by operating a second NCM. The second NCM can use a common set of parameters in determining the second feature values. The processing unit can determine respective expectation values of some of the actions of the plurality of actions based on the first feature value and the respective second feature values. The processing unit can select a first action of the plurality of actions based on at least one of the expectation values. In some examples, the processing unit can operate an NCM to determine expectation values based on information of a session and information of respective actions.