Abstract: Techniques are provided for training, by a system operatively coupled to a processor, an attention weighted recurrent neural network encoder-decoder (AWRNNED) using an iterative process based on one or more paragraphs of agent sentences from respective transcripts of one or more conversations between one or more agents and one or more customers, and based on one or more customer response sentences from the respective transcripts, and generating, by the system, one or more groups respectively comprising one or more agent sentences and one or more customer response sentences selected based on attention weights of the AWRNNED.

Abstract: A virtual change database system that supports iterative and parallel database application development is disclosed. The system stores a common set of base physical data and a plurality of sets of virtual changes. Each set of virtual changes is associated with a database object. A database application may access a database object in the database by using the virtual version of the object to extract the object's data content from the common base physical data. The database system present a first query response to (i) a first application based on the set of base physical data and (ii) a first set of virtual changes for a particular database object, while also presenting a second query response to a second application based on the set of base physical data and a second, different set of virtual changes for the particular database object.

Abstract: Techniques for identifying representative patients from a patient group are provided. Based on an outcome of interest, one or more patients can be grouped according to phenotyping features associated with the outcome of interest. Additionally, in response to grouping the one or more patients, a representative patient of the one or more patients can be determined based on values associated with the phenotyping features.

Abstract: Systems, computer-implemented methods and/or computer program products that facilitate predicting personalized risks based on intrinsic factors and extrinsic factors are provided. In one example, a computer-implemented method comprises: collecting, by a system operatively coupled to a processor, intrinsic factors and extrinsic factors associated with infectious diseases; generating, by the system, a probabilistic model based on the intrinsic factors and extrinsic factors, wherein the model incorporates node characteristics into infection probability; and refining, by the system, the model through concurrently learning respective node thresholds and hidden infection network structure of the model.

Abstract: Techniques facilitating attention based sequential image processing are provided. A system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise an initialization component that can perform self-attention based training on a model that comprises context information associated with a sequence of images. Images of the sequence of images can be selected during the self-attention based training. The computer executable components can also comprise a localization component that can extract local information from the images selected during the self-attention based training based on the context information. In addition, the computer executable components can also comprise an integration component that can update the model based on an end-to-end integrated attention training framework comprising the context information and the local information.

Abstract: A dataset regarding a plurality of applications is obtained. A set of parameters is determined from the dataset, comprising at least a sample performance trajectory, a risk factor, and a performance outcome. A maximum likelihood of each performance outcome is determined using a likelihood function, the likelihood function being a mixture model of a trajectory model and an outcome model. The set of parameters is updated according to the maximum likelihood of each performance outcome. A performance trajectory model is built according to the updated set of parameters. The plurality of applications is then grouped into subgroups according to the performance trajectory model, each subgroup containing one or more applications, and each of the one or more applications in a given subgroup having a same or similar trajectory to each other. An alert associated with the applications in at least one of subgroups may be generated.

Abstract: Patient treatment may be optimized using Recurrent Neural Network (RNN) based state simulation and Reinforcement learning (RL) techniques to simulate future states and actions. A RNN state simulator and a RL action generator may be trained using patient data such as historical states and actions. The RL action generator may be optimized by applying the RNN state simulator to simulating future states and applying the RL action generator to generate recommended actions based on the simulated future states. This process may be iteratively performed until a computational convergence is reached by the RL action generator which may indicate that the RL action generator has been optimized. A patient state may be fed into the optimized RL action generator to generate an optimal recommended treatment action.

Abstract: Techniques are described that facilitate automatically providing entities with rephrased versions of standard answers. In one embodiment, a computer-implemented is provided that comprises determining, by a device operatively coupled to a processor, a talking style of a plurality of talking styles that an entity is associated with based on reception of natural language input from the entity proposing a question related to a defined topic. The method further comprises selecting, by the device based on the talking style, an answer rephrasing model from a plurality of answer rephrasing models respectively configured to generate different rephrased versions of a standard answer to the question, and employing, by the device, the answer rephrasing model to generate a rephrased version of the standard that corresponds to the talking style.

Abstract: Techniques are provided for training, by a system operatively coupled to a processor, an attention weighted recurrent neural network encoder-decoder (AWRNNED) using an iterative process based on one or more paragraphs of agent sentences from respective transcripts of one or more conversations between one or more agents and one or more customers, and based on one or more customer response sentences from the respective transcripts, and generating, by the system, one or more groups respectively comprising one or more agent sentences and one or more customer response sentences selected based on attention weights of the AWRNNED.

Abstract: Techniques are provided for training, by a system operatively coupled to a processor, an attention weighted recurrent neural network encoder-decoder (AWRNNED) using an iterative process based on one or more paragraphs of agent sentences from respective transcripts of one or more conversations between one or more agents and one or more customers, and based on one or more customer response sentences from the respective transcripts, and generating, by the system, one or more groups respectively comprising one or more agent sentences and one or more customer response sentences selected based on attention weights of the AWRNNED.

Abstract: Patient treatment may be optimized using Recurrent Neural Network (RNN) based state simulation and Reinforcement learning (RL) techniques to simulate future states and actions. A RNN state simulator and a RL action generator may be trained using patient data such as historical states and actions. The RL action generator may be optimized by applying the RNN state simulator to simulating future states and applying the RL action generator to generate recommended actions based on the simulated future states. This process may be iteratively performed until a computational convergence is reached by the RL action generator which may indicate that the RL action generator has been optimized. A patient state may be fed into the optimized RL action generator to generate an optimal recommended treatment action.

Abstract: A method, system, and computer program product for obtaining a candidate event sequence that includes at least one event for achieving a goal, obtaining a reference event sequence, the candidate event sequence comprising at least one event that is not comprised in the reference event sequence, comparing an effectiveness of the candidate event sequence on the goal and an effectiveness of the reference event sequence on the goal, and identifying the candidate event sequence as an effective sequence for achieving the goal in response to the effectiveness of the candidate event sequence being better than the effectiveness of the reference event sequence.

Abstract: A system for tracking cumulative motor vehicle risk includes a satellite navigation system receiver disposed within a motor vehicle and configured to determine a present location of the motor vehicle. A computer processor receives the determined present location of the motor vehicle from the satellite navigation system receiver and generates a traveled route therefrom. A first computer server receives a plurality of motor vehicle claims records, determines a plurality of motor vehicle accident locations from the plurality of motor vehicle claims records, and generates a motor vehicle accident heat map from the plurality of motor vehicle accident locations. A second computer server determines a cumulative risk exposure of the motor vehicle based on the generated traveled route and the generated motor vehicle accident heat map.

Abstract: Techniques facilitating attention based sequential image processing are provided. A system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise an initialization component that can perform self-attention based training on a model that comprises context information associated with a sequence of images. Images of the sequence of images can be selected during the self-attention based training. The computer executable components can also comprise a localization component that can extract local information from the images selected during the self-attention based training based on the context information. In addition, the computer executable components can also comprise an integration component that can update the model based on an end-to-end integrated attention training framework comprising the context information and the local information.

Abstract: Techniques facilitating attention based sequential image processing are provided. A system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise an initialization component that can perform self-attention based training on a model that comprises context information associated with a sequence of images. Images of the sequence of images can be selected during the self-attention based training. The computer executable components can also comprise a localization component that can extract local information from the images selected during the self-attention based training based on the context information. In addition, the computer executable components can also comprise an integration component that can update the model based on an end-to-end integrated attention training framework comprising the context information and the local information.

Abstract: A method and system of imputing corrupted sequential data is provided. A plurality of input data vectors of a sequential data is received. For each input data vector of the sequential data, the input data vector is corrupted. The corrupted input data vector is mapped to a staging hidden layer to create a staging vector. The input data vector is reconstructed based on the staging vector, to provide an output data vector. adjusted parameter of the staging hidden layer is iteratively trained until it is within a predetermined tolerance of a loss function. A next input data vector of the sequential data is predicted based on the staging vector. The predicted next input data vector is stored.

Abstract: This disclosure provides a computer-implemented method. The method may include extracting one or more features based on a first utterance from a first interlocutor in a dialog and a second utterance from a second interlocutor in the dialog. The method may further include inferring one or more personality traits of the first interlocutor based on the one or more extracted features from the dialog.

Abstract: Techniques are described that facilitate automatically providing entities with rephrased versions of standard answers. In one embodiment, a computer-implemented is provided that comprises determining, by a device operatively coupled to a processor, a talking style of a plurality of talking styles that an entity is associated with based on reception of natural language input from the entity proposing a question related to a defined topic. The method further comprises selecting, by the device based on the talking style, an answer rephrasing model from a plurality of answer rephrasing models respectively configured to generate different rephrased versions of a standard answer to the question, and employing, by the device, the answer rephrasing model to generate a rephrased version of the standard that corresponds to the talking style.

Abstract: Techniques are described that facilitate automatically providing entities with rephrased versions of standard answers. In one embodiment, a computer-implemented is provided that comprises determining, by a device operatively coupled to a processor, a talking style of a plurality of talking styles that an entity is associated with based on reception of natural language input from the entity proposing a question related to a defined topic. The method further comprises selecting, by the device based on the talking style, an answer rephrasing model from a plurality of answer rephrasing models respectively configured to generate different rephrased versions of a standard answer to the question, and employing, by the device, the answer rephrasing model to generate a rephrased version of the standard that corresponds to the talking style.

Abstract: Embodiments include methods, and mobile computing devices, and computer program products for creating personalized photo albums on mobile computing devices based on social media data. Aspects include: accessing, via mobile computing device, various photos taken by a user of mobile computing device, retrieving, from one or more social media streams, various media photos posted by user of the mobile computing device, extracting image features from the photos and the media photos, and text features from the media photos, generating photo clusters based on the image features of the photos, and media photo clusters based on the image features of the media photos, respectively, matching the photo clusters and the media photo clusters, tagging the photo clusters and the media photo clusters matched based on the text features extracted from the media photos, and generating a personalized photo album based on the photo clusters tagged and the media photo clusters tagged.