Abstract: A method, apparatus and computer program product for establishing a logical connection between an indirect utterance and a transaction is described. An indirect utterance is received from a user as an input to a conversational system. The indirect utterance is parsed to a first logical form. A first set of predicates and terms is mapped from the first logical form to a first subgraph in a knowledge graph. A second set of predicates and terms is mapped from a second logical form belonging to a transaction to a second subgraph of the knowledge graph. A best path in the knowledge graph between the first subgraph and the second subgraph is searched for while transforming the first logical form using the node and edge labels along the best path to generate an intermediate logical form. A system action is performed for a transaction if a graph structure of the intermediate logical form matches the graph structure of the logical form of the transaction above a threshold.

Abstract: A method, apparatus and computer program product for responding to an indirect utterance in a dialogue between a user and a conversational system is described. An indirect utterance is received. A parse structure of the indirect utterance is generated. The indirect utterance is an utterance which does not match a user goal expressed as elements of a knowledge graph. The parse structure is connected through the knowledge graph to a user goal to issue a user request which is not stated in the indirect utterance. The parse structure is connected using a matching process which matches the parse structure with the connected user goal in the knowledge graph according to a similarity of the parse structure and a portion of the knowledge graph including the connected user goal. A system response is performed based on the connected user goal.

Abstract: The example computer-implemented method may comprise computing, by a generator processor on each of a plurality of learners, a gradient for a mini-batch using a current weight at each of the plurality of learners. The method may also comprise generating, by the generator processor on each of the plurality of learners, a plurality of triples, wherein each of the triples comprises the gradient, the weight index of the current weights used to compute the gradient, and a mass of the gradient. The method may further comprise performing, by a reconciler processor on each of the plurality of learners, an allreduce operation on the plurality of triples to obtain an allreduced triple sequence. Additionally, the method may comprise updating, by the reconciler processor on each of the plurality of learners, the current weight at each of the plurality of learners to a new current weight using the allreduced triple sequence.

Abstract: A method, apparatus and computer program product for responding to an indirect utterance in a dialogue between a user and a conversational system is described. An indirect utterance is received. A parse structure of the indirect utterance is generated. The indirect utterance is an utterance which does not match a user goal expressed as elements of a knowledge graph. The parse structure is connected through the knowledge graph to a user goal to issue a user request which is not stated in the indirect utterance. The parse structure is connected using a matching process which matches the parse structure with the connected user goal in the knowledge graph according to a similarity of the parse structure and a portion of the knowledge graph including the connected user goal. A system response is performed based on the connected user goal.

Abstract: A method, apparatus and computer program product for responding to an indirect utterance in a dialog between a user and a conversational system is described. An indirect utterance is received. A parse structure of the indirect utterance is generated. The indirect utterance is an utterance which does not match a user goal expressed as elements of a knowledge graph. The parse structure is connected through the knowledge graph to a user goal to issue a request which is not stated in the indirect utterance. A system response is performed, where the system response is a dialog system response based on a combination of the parse structure and the connected user goal.

Abstract: A method, apparatus and computer program product for establishing a logical connection between an indirect utterance and a transaction is described. An indirect utterance is received from a user as an input to a conversational system. The indirect utterance is parsed to a first logical form. A first set of predicates and terms is mapped from the first logical form to a first subgraph in a knowledge graph. A second set of predicates and terms is mapped from a second logical form belonging to a transaction to a second subgraph of the knowledge graph. A best path in the knowledge graph between the first subgraph and the second subgraph is searched for while transforming the first logical form using the node and edge labels along the best path to generate an intermediate logical form. A system action is performed for a transaction if a graph structure of the intermediate logical form matches the graph structure of the logical form of the transaction above a threshold.

Abstract: A method, apparatus and computer program product for responding to an indirect utterance in a dialogue between a user and a conversational system is described. An indirect utterance is received. A parse structure of the indirect utterance is generated. The indirect utterance is an utterance which does not match a user goal expressed as elements of a knowledge graph. The parse structure is connected through the knowledge graph to a user goal to issue a request which is not stated in the indirect utterance. A system response is performed, where the system response is a dialogue system response based on a combination of the parse structure and the connected user goal.

Abstract: Running a global production rule on data distributed over a plurality of machines may comprise receiving a local production rule that can run on each of the plurality of machines to jointly accomplish a global computation specified by the global production rule. The local production rule may be deployed to each of the plurality of machines, each of which stores a portion of the data and runs an instance of a rules engine that can run the local production rule. The plurality of machines are enabled to communicate intermediate data produced by the instance of the rules engine running the local production rule on said each of the machines. Coordinating between the plurality of machines is enabled to synchronize one or more local computations performed locally according to the local production rule on said each machine.

Abstract: The present information processing apparatus executes fault-tolerant distributed computing through a network and the information processing apparatus comprises: a finish initiator that creates a finish state on a home node; an activity creator that instructs to create at least one activity on a remote node; an activity launcher that allows to store in a resilient store a value indicating that at least one live activity is present on the remote node; an activity closer that decreases the number in the local memory when the living activity is completed and resets the value in the resilient store to indicate that no live activity is present on the remote node; and a finish closer that closes the finish state when the value stored in the resilient store indicates an absence of remote nodes having at least one live activity.

Abstract: The example computer-implemented method may comprise computing, by a generator processor on each of a plurality of learners, a gradient for a mini-batch using a current weight at each of the plurality of learners. The method may also comprise generating, by the generator processor on each of the plurality of learners, a plurality of triples, wherein each of the triples comprises the gradient, the weight index of the current weights used to compute the gradient, and a mass of the gradient. The method may further comprise performing, by a reconciler processor on each of the plurality of learners, an allreduce operation on the plurality of triples to obtain an allreduced triple sequence. Additionally, the method may comprise updating, by the reconciler processor on each of the plurality of learners, the current weight at each of the plurality of learners to a new current weight using the allreduced triple sequence.

Abstract: Running a global production rule on data distributed over a plurality of machines may comprise receiving a local production rule that can run on each of the plurality of machines to jointly accomplish a global computation specified by the global production rule. The local production rule may be deployed to each of the plurality of machines, each of which stores a portion of the data and runs an instance of a rules engine that can run the local production rule. The plurality of machines are enabled to communicate intermediate data produced by the instance of the rules engine running the local production rule on said each of the machines. Coordinating between the plurality of machines is enabled to synchronize one or more local computations performed locally according to the local production rule on said each machine.

Abstract: Running a global production rule on data distributed over a plurality of machines may comprise receiving a local production rule that can run on each of the plurality of machines to jointly accomplish a global computation specified by the global production rule. The local production rule may be deployed to each of the plurality of machines, each of which stores a portion of the data and runs an instance of a rules engine that can run the local production rule. The plurality of machines are enabled to communicate intermediate data produced by the instance of the rules engine running the local production rule on said each of the machines. Coordinating between the plurality of machines is enabled to synchronize one or more local computations performed locally according to the local production rule on said each machine.

Abstract: Automated feature construction for algorithm portfolios in machine learning is provided. A gray scale image is generated from a text representing a problem instance. The gray scale image is rescaled or reshaped to a predefined size that is smaller than an initial size of the gray scale image. The rescaled gray scale image represents features of the problem instance. The rescaled gray scale image is input as features to a machine learning-based convolutional neural network. Based on the rescaled gray scale image, the machine learning-based convolutional neural network is automatically trained to learn to automatically determine one or more problem solvers from a portfolio of problem solvers suited for solving the problem instance.

Abstract: The present information processing apparatus executes fault-tolerant distributed computing through a network and the information processing apparatus comprises: a finish initiator that creates a finish state on a home node; an activity creator that instructs to create at least one activity on a remote node; an activity launcher that allows to store in a resilient store a value indicating that at least one live activity is present on the remote node; an activity closer that decreases the number in the local memory when the living activity is completed and resets the value in the resilient store to indicate that no live activity is present on the remote node; and a finish closer that closes the finish state when the value stored in the resilient store indicates an absence of remote nodes having at least one live activity.

Abstract: Executing a map reduce sequence may comprise executing all jobs in the sequence by a collection of a plurality of processes with each process running one or more mappers, combiners, partitioners and reducers for each job, and transparently sharing heap state between the jobs to improve metrics associated with the job. Processes may communicate among themselves to coordinate completion of map, shuffle and reduce phases, and completion of said all jobs in the sequence.

Abstract: Running a global production rule on data distributed over a plurality of machines may comprise receiving a local production rule that can run on each of the plurality of machines to jointly accomplish a global computation specified by the global production rule. The local production rule may be deployed to each of the plurality of machines, each of which stores a portion of the data and runs an instance of a rules engine that can run the local production rule. The plurality of machines are enabled to communicate intermediate data produced by the instance of the rules engine running the local production rule on said each of the machines. Coordinating between the plurality of machines is enabled to synchronize one or more local computations performed locally according to the local production rule on said each machine.

Abstract: A method for increasing performance of an operation on a distributed memory machine is provided. Asynchronous parallel steps in the operation are transformed into synchronous parallel steps. The synchronous parallel steps of the operation are rearranged to generate an altered operation that schedules memory accesses for increasing locality of reference. The altered operation that schedules memory accesses for increasing locality of reference is mapped onto the distributed memory machine. Then, the altered operation is executed on the distributed memory machine to simulate local memory accesses with virtual threads to check cache performance within each node of the distributed memory machine.

Abstract: Interactive iterative program parallelization based on dynamic feedback program parallelization, in one aspect, may identify a ranked list of one or more candidate pieces of code each with one or more source refactorings that can be applied to parallelize the code, apply at least one of the one or more refactorings to create a revised code, and determine performance data associated with the revised code. The performance data may be used to make decisions on identifying next possible ranked list of refactorings.

Abstract: Executing a map reduce sequence may comprise executing all jobs in the sequence by a collection of a plurality of processes with each process running zero or more mappers, combiners, partitioners and reducers for each job, and transparently sharing heap state between the jobs to improve metrics associated with the job. Processes may communicate among themselves to coordinate completion of map, shuffle and reduce phases, and completion of said all jobs in the sequence.

Abstract: Executing a map reduce sequence may comprise executing all jobs in the sequence by a collection of a plurality of processes with each process running one or more mappers, combiners, partitioners and reducers for each job, and transparently sharing heap state between the jobs to improve metrics associated with the job. Processes may communicate among themselves to coordinate completion of map, shuffle and reduce phases, and completion of said all jobs in the sequence.