Abstract: Dual-modality relation networks for audio-visual event localization can be provided. A video feed for audio-visual event localization can be received. Based on a combination of extracted audio features and video features of the video feed, informative features and regions in the video feed can be determined by running a first neural network. Based on the informative features and regions in the video feed determined by the first neural network, relation-aware video features can be determined by running a second neural network. Based on the informative features and regions in the video feed, relation-aware audio features can be determined by running a third neural network. A dual-modality representation can be obtained based on the relation-aware video features and the relation-aware audio features by running a fourth neural network. The dual-modality representation can be input to a classifier to identity an audio-visual event in the video feed.

Abstract: A domain of an input dataset is identified and one or more archived domain knowledge features corresponding to the identified domain are identified. One or more user feature definitions for one or more user features defined by a user are inputted. The identified archived domain knowledge features and the user features are processed to generate a set of candidate features for presentation to the user. A selection of a subset of the candidate features is obtained from the user and one or more predictive models are generated based on the selected features.

Abstract: A computer-implemented method includes using an embedding network to generate prototypical vectors. Each prototypical vector is based on a corresponding label associated with a first domain. The computer-implemented method also includes using the embedding network to generate an in-domain test vector based on at least one data sample from a particular label associated with the first domain and using the embedding network to generate an out-of-domain test vector based on at least one other data sample associated with a different domain. The computer-implemented method also includes comparing the prototypical vectors to the in-domain test vector to generate in-domain comparison values and comparing the prototypical vectors to the out-of-domain test vector to generate out-of-domain comparison values. The computer-implemented method also includes modifying, based on the in-domain comparison values and the out-of-domain comparison values, one or more parameters of the embedding network.

Abstract: A computerized method, system and computer program product for automatically generating question and answer pairs. One embodiment of the method may comprise receiving an input document, the input document comprising content. The method may further comprise generating, by a first machine learning model from the input document, a plurality of answers based on the content of the input document, and generating, by a second machine learning model from the input document, a question for each of the plurality of answers to form a plurality of question-answer pairs. The method may further comprise ranking, by a third machine learning model, the plurality of question-answer pairs, selecting a predetermined number of highest ranked question-answer pairs, and returning the predetermined number of highest ranked question-answer pairs to a user.

Abstract: A computerized method, system and computer program product for building a dialogue flow. One embodiment of the method may comprise receiving an input document, the input document comprising content, and generating, by a question-answer pipeline, a plurality of question-answer pairs from the content of the input document. For each question-answer pair, the method may further comprise feeding the question of the question-answer pair into an intent of a dialogue flow structure, and feeding the answer of the question-answer pair as one response of the intent. The method may further comprise tagging each of the plurality of question-answer pairs with a corresponding document section index, reading, by a conversational agent, the input document to a user, pausing the reading when the conversational agent reaches one of the document section indices in the input document, and in response, reading the question corresponding to the document section indicia to the user.

Abstract: A processor may receive a video including a plurality of video frames in sequence and a question regarding the video. For a video frame in the plurality of video frames, a processor may parse the video frame into objects and relationships between the objects, and create a subgraph of nodes representing objects and edges representing the relationships, where parsing and creating are performed for each video frame in the plurality of video frames, where a plurality of subgraphs can be created. A processor may create a hypergraph connecting subgraphs by learning relationships between the nodes of the subgraphs, where a hyper-edge is created to represent a relationship between at least one node of one subgraph and at least one node of another subgraph in the plurality of subgraphs. A processor may generate an answer to the question based on the hypergraph.

Abstract: Embodiments relate to a system, program product, and method for leveraging cognitive systems to facilitate the automated data table discovery for automated machine learning, and, more specifically, to leveraging a trained cognitive system to automatically search for additional data in an external data source that may be merged with an initial user-selected data table to generate a more robust machine learning model. Manual efforts to find and validate data appropriate for building and training a particular model for a particular task are significantly reduced. Specifically, a learning-based approach to leverage with machine learning models to automatically discover related datasets and join the datasets for a given initial dataset is disclosed herein. Operations that include dataset selection facilitate continued reinforcement learning of the systems.

Abstract: Techniques regarding one or more automated machine learning processes that analyze time series data are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a time series analysis component that selects a machine learning pipeline for meta transfer learning on time series data by sequentially allocating subsets of training data from the time series data amongst a plurality of machine learning pipeline candidates.

Abstract: Mechanisms are provided for performing artificial intelligence-based video question answering. A video parser parses an input video data sequence to generate situation data structure(s), each situation data structure comprising data elements corresponding to entities, and first relationships between entities, identified by the video parser as present in images of the input video data sequence. First machine learning computer model(s) operate on the situation data structure(s) to predict second relationship(s) between the situation data structure(s). Second machine learning computer model(s) execute on a received input question to predict an executable program to execute to answer the received question. The program is executed on the situation data structure(s) and predicted second relationship(s). An answer to the question is output based on results of executing the program.

Abstract: Systems, computer-implemented methods, and computer program products to facilitate conditional parallel coordinates in automated artificial intelligence with constraints are provided. According to an embodiment, 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 a visualization component that renders a pipeline constraint as a constraint axis having constraint scores of machine learning pipelines in a conditional parallel coordinates visualization. The computer executable components can further comprise a model generation component that generates a machine learning model based on the constraint scores of the machine learning pipelines.

Abstract: A method for implementing video frame synthesis using a tensor neural network includes receiving input video data including one or more missing frames, converting the input video data into an input tensor, generating, through tensor completion based on the input tensor, output video data including one or more synthesized frames corresponding to the one or more missing frames by using a transform-based tensor neural network (TTNet) including a plurality of phases implementing a tensor iterative shrinkage thresholding algorithm (ISTA), and obtaining a loss function based on the output video data.

Abstract: Embodiments for providing automated machine learning visualization. Machine learning tasks, transformers, and estimators may be received into one or more machine learning composition modules. The machine learning composition modules generate one or more machine learning models. A machine learning model pipeline is a sequence of transformers and estimators and an ensemble of machine learning pipelines are an ensemble of machine learning pipelines. A machine learning model pipeline, an ensemble of a plurality of machine learning model pipelines, or a combination thereof, along with corresponding metadata, may be generated using the machine learning composition modules. Metadata may be extracted from the machine learning model pipeline, the ensemble of a plurality of machine learning model pipelines, or combination thereof.

Abstract: Systems, computer-implemented methods, and/or computer program products facilitating a process to identify and respond to a primary electronic message are provided. According to an embodiment, 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 include a determination component can determine that a primary electronic message has not received a response electronic message. An analysis component can generate a generated electronic message addressing the informational or emotional content of the primary electronic message. In one or more embodiments, an updating component can update the analytical model based on one or more feedbacks to the generated electronic message, where the analytical model can remain active while being updated.

Abstract: A bi-directional spatial-temporal transformer neural network (BDSTT) is trained to predict original coordinates of a skeletal joint in a specific frame through relative relationships of the skeletal joint to other joints and to the state of the skeletal joint in other frames. Obtain a plurality of frames comprising coordinates of the skeletal joint and coordinates of other joints. Produce a spatially masked frame by masking the original coordinates of the skeletal joint. Provide the specific frame, the spatially masked frame, and at least one more frame to a coordinate prediction head of the BDSTT. Obtain, from the coordinate prediction head, a prediction of coordinates for the skeletal joint. Adjust parameters of the BDSTT until a mean-squared error, between the prediction of coordinates for the skeletal joint and the original coordinates of the skeletal joint, converges.

Abstract: A dataset including features and values associated with the features can be received. Each of the features in the dataset can be mapped to a corresponding node in a knowledge graph based on the concept represented by the corresponding node. The knowledge graph can be traversed to find a candidate node connected to at least one mapped node, the candidate node not being mapped to a feature in the dataset. A concept associated with the candidate node can be identified as a new feature. A machine learning model pipeline can use the features in the dataset and the new feature to select a subset of features for training a machine learning model.

Abstract: In an approach to generating question answer pairs, one or more computer processors receive a corpus of text. One or more computer processors extract one or more key concepts from the corpus of text. Based on the one or more key concepts, one or more computer processors generate one or more questions associated with the key concepts, where the one or more key concepts are answers to the one or more generated questions. One or more computer processors display the one or more generated questions and the answers to the one or more generated questions.

Abstract: An approach is provided in which a method, system, and program product display, on a user interface, at least one of a set of node split parameters in response to receiving a first user selection that selects a node in a decision tree. The selected node branches to a set of child nodes in the decision tree based on the set of node split parameters. The method, system, and program product adjust at least one of the set of node split parameters of the selected node in response to receiving a second user selection. The method, system, and program product modify the decision tree based on the adjusted set of node split parameters. The modified decision tree includes a modified set of child nodes that branch from the selected node based on the adjusted set of node split parameters.

Abstract: Systems and methods for creating presentation slides. A slide title is received and portions of source documents relevant to the title are identified based on a dense vector information retrieval machine learning process. An abstractive summary of the portions is generated based on a long form question answering machine learning process. A first presentation slide is created with the abstractive summary and the title. The first presentation slide is presented to an operator and an input indicating one of accepting or rejection the abstractive summary is received. Based on the input that indicating rejecting the abstractive summary, the abstractive summary is removed from the presentation slide and negative training feedback for the abstractive summary is provided to at least one of the dense vector information retrieval machine learning process or the long form question answering machine learning process.

Abstract: To automate time series forecasting machine learning pipeline generation, a data allocation size of time series data may be determined based on one or more characteristics of a time series data set. The time series data may be allocated for use by candidate machine learning pipelines based on the data allocation size. Features for the time series data may be determined and cached by the candidate machine learning pipelines. Predictions of each of the candidate machine learning pipelines using at least the one or more features may be evaluated. A ranked list of machine learning pipelines may be automatically generated from the candidate machine learning pipelines for time series forecasting based upon evaluating predictions of each of the one or more candidate machine learning pipelines.

Abstract: Unsupervised learning for video classification. One or more features from one or more video clips are extracted using a spatial-temporal encoder. The one or more extracted features are processed, using a video instance discrimination task, to generate a classification label, the classification label indicating whether two of the video clips are from a same video. The one or more extracted features are processed, using a pair-wise speed discrimination task, to generate a comparison label, the comparison label indicating a relative playback speed between two given video clips. A search is performed in a video database for a video that is similar to a given video based on the comparison label.