Abstract: A computer implemented method for analyzing feedback with respect to a virtual assistant includes identifying a technical support problem and a corresponding resolution, wherein the technical support problem corresponds to a query, and wherein the corresponding resolution corresponds to the virtual assistant's response, collecting user feedback provided by one or more users corresponding to the technical support problem and the corresponding resolution, creating a set of user profiles corresponding to the one or more users, generating weighted user feedback according to the set of user profiles, identifying contradictory feedback patterns corresponding to the one or more users, adjusting the set of user profiles according to the identified contradictory feedback patterns, and recommending improvements to the identified corresponding resolution.

Abstract: An approach to ranking identified technical solutions summaries may be provided. The approach may include extracting data from technical tickets, subject matter expert reports, and online forum data. The approach may include receiving data relating to prior applications of one or more technical solutions. Steps associated with a technical solution may be included in the information from the prior application of the technical solutions and updated based on the information from prior applications of technical solutions. The approach may include generating a risk score and a cost score for the updated technical solution based on contextual factors associated with a user or machine. The approach may include enriching a static summary for the technical solution with the cost and risk score. The approach may include ranking the enriched summary against multiple potential technical solutions.

Abstract: One embodiment of the invention provides a method for terminology ranking for use in natural language processing. The method comprises receiving a list of terms extracted from a corpus, where the list comprises a ranking of the terms based on frequencies of the terms across the corpus. The method further comprises accessing a domain ontology associated with the corpus, and re-ranking the list based on the domain ontology. The resulting re-ranked list comprises a different ranking of the terms based on relevance of the terms using knowledge from the domain ontology. The method further comprises generating clusters of terms via a trained model adapted to the corpus, and boosting a rank of at least one term of the re-ranked list based on the clusters to increase a relevance of the at least one term using knowledge from the trained model.

Abstract: A method, system, and computer program product for automated evaluation of information retrieval systems are provided. The method accesses a natural language query from a set of natural language queries. The natural language query is associated with a query difficulty level. The method generates one or more natural language responses to the natural language natural language query. Each natural language response is associated with at least one facet of the plurality of facets. The method generates a set of feedback cues. A set of search results for the natural language query are returned. The set of search results include a highest ranked natural language response of the one or more natural language responses. The method generates an evaluation result for the HCIR system for the query difficulty level based on the one or more natural language responses, the set of search results, and the set of feedback cues.

Abstract: Various embodiments for optimizing memory bandwidth in a disaggregated computing system, by a processor device, are provided. Respective memory devices are assigned to respective processor devices in the disaggregated computing system, the disaggregated computing system having at least a pool of the memory devices and a pool of the processor devices. An analytic function is performed on data resident in the pool of the memory devices using memory bandwidth not currently committed to a primary compute task.

Abstract: An approach to controlling smart devices in response to detecting events may be provided. The location data of a user may be received, along with date and time for the location data. The location may be compared to a daily schedule to determine whether an event has occurred. If the location data is determined to be outside of the daily schedule it is determined an event has occurred. The event is then compared to other logged events within a historical event database, to determine if the event is similar to any past events. If the event is determined to be similar to a past event, the state of smart devices connected to an event driven smart device control environment are changed to mirror the state they were in at during determined similar event.

Abstract: Systems, devices, computer-implemented methods, and/or computer program products that facilitate event schema induction from unstructured or semi-structured data. In one example, a system can comprise a processor that executes computer executable components stored in memory. The computer executable components can comprise a schema component and a retrieval component. The schema component can derive an event schema for a document corpus using parsing results obtained from the document corpus. The retrieval component can populate a response to a query with a document of the document corpus using events extracted from the query and the document using the event schema.

Abstract: Methods, systems, and computer program products for automatically classifying heterogeneous documents using machine learning techniques are provided herein. A computer-implemented method includes extracting multiple features from one or more sets of heterogeneous documents; arranging at least a portion of the extracted features into multiple hierarchically-defined classes; selecting one or more of the documents associated with each of the multiple hierarchically-defined classes; training at least one machine learning model using at least a portion of the selected documents; and automatically classifying at least one input document into one or more of the multiple hierarchically-defined classes by processing one or more portions of the at least one input document using the at least one trained machine learning model.

Abstract: A method of predicting future performance of a data center battery system includes receiving information related to a data center battery system in real time, analyzing the received information in real time, predicting a future performance of the data center battery system, providing the predicted future performance of the data center battery system to a data center control system, and optimizing the data center battery system based on the predicting.

Abstract: Embodiments are provided that relate to a computer system, a computer program product, and a computer-implemented method for improving performance of a virtual dialog agent system employing an automated virtual dialog agent. Embodiments involve generating ground truth (GT) from a user's knowledge base, and leveraging the GT to evaluate how the virtual dialog agent performs with the GT. The evaluation measures quality of a multi-turn virtual dialog, and generates a remediation plan directed at an algorithmic improvement of the virtual dialog agent.

Abstract: Embodiments of the present invention provide a computer system, a computer program product, and a method that comprises analyzing a performed query by identifying a plurality of indicative markers based on a pre-stored classification database associated with the performed query; generating a plurality of facets based on the analysis of the performed query; selecting at least two facets within the generated plurality of facets by determining a quantitative similarity value between each respective facet and the plurality of identified indicative markers associated with the performed query; dynamically ranking the selected facets by prioritizing the selected facets based on a calculated overall score associated with assigned weighted values for each selected facet in the generated plurality of facets using a supervised machine learning algorithm; and displaying the dynamically ranked facets within a user interface of a computing device associated with a user.

Abstract: In an approach to content driven predictive auto completion of IT queries, an input phrase for an inquiry is received, where the input phrase is a sequence of words. Next words for the input phrase are predicted, where the prediction is based on a deep neural network model that has been trained with a corpus of documents for a specific domain. The next words are appended to the input phrase to create one or more predicted phrases. The predicted phrases are sorted, where the predicted phrases are sorted based on a similarity computation between the predicted phrases and the corpus of documents for the specific domain.

Abstract: Embodiments for optimizing dynamic resource allocations for storage-dependent workloads in a disaggregated computing environment. A new workload is assigned to a subset of a plurality of processors, the subset of processors assigned a subset of a plurality of memory devices associated with a plurality of storage devices. A determination is made that the new workload is categorized as a storage-dependent workload having a storage need which can be met primarily by a subset of the storage devices after having identified whether data requests associated with the new workload can be satisfied by the subset of memory devices. Pursuant to determining the new workload is the storage-dependent workload, a storage related action is proactively performed to increase efficiency of the new workload prior to commencement of a performance of the new workload.

Abstract: Disclosed embodiments provide techniques for technical support. Previously reported problem reports are analyzed and symptoms are extracted. Solutions are associated with the previously reported problem reports. A newly submitted user problem is analyzed and symptoms are extracted and compared with the symptoms of the previously reported problems. Solutions are then associated with the user problem based on relevance to symptoms, product type, and/or other factors.

Abstract: A method, system, and computer program product for automated evaluation of information retrieval systems are provided. The method accesses a natural language query from a set of natural language queries. The natural language query is associated with a query difficulty level. The method generates one or more natural language responses to the natural language natural language query. Each natural language response is associated with at least one facet of the plurality of facets. The method generates a set of feedback cues. A set of search results for the natural language query are returned. The set of search results include a highest ranked natural language response of the one or more natural language responses. The method generates an evaluation result for the HCIR system for the query difficulty level based on the one or more natural language responses, the set of search results, and the set of feedback cues.

Abstract: Server resources in a data center are disaggregated into shared server resource pools, including an accelerator (e.g., FPGA) pool. Servers are constructed dynamically, on-demand and based on workload requirements, by allocating from these resource pools. According to this disclosure, accelerator utilization in the data center is managed proactively by assigning accelerators to workloads in a fine granularity and agile way, and de-provisioning them when no longer needed. In this manner, the approach is especially advantageous to automatically provision accelerators for data analytic workloads. The approach thus provides for a “micro-service” enabling data analytic workloads to automatically and transparently use FPGA resources without providing (e.g., to the data center customer) the underlying provisioning details. Preferably, the approach dynamically determines the number and the type of FPGAs to use, and then during runtime auto-scales the FPGAs based on workload.

Abstract: Respective memory devices are assigned to respective processor devices in a disaggregated computing system, the disaggregated computing system having at least a pool of the memory devices and a pool of the processor devices. An iterative learning algorithm is used to define data boundaries of a dataset for performing an analytic function on the dataset simultaneous to a primary compute task, unrelated to the analytic function, being performed on the dataset in the pool of memory devices using memory bandwidth not currently committed to the primary compute task, thereby efficiently employing the unused memory bandwidth to prevent underutilization of the pool of memory devices.

Abstract: A method, a computer program product, and a computer system induce knowledge from a knowledge graph. The method includes receiving a request indicative of a domain. The method includes determining a corpus corresponding to the domain and determining a quality of the corpus in generating the knowledge graph relative to a quality threshold. If the quality threshold is not met, the method includes determining a candidate expansion corpus to incorporate further data therefrom into the corpus relative to an expansion threshold. If the expansion threshold is met, the method includes generating an expanded corpus by expanding the corpus with the further data. The method includes generating the knowledge graph based on the expanded corpus from which the knowledge is induced and generating a response to the request based on the knowledge graph.

Abstract: Given a skeleton knowledge graph including first terms in respective nodes, wherein first terms in connected nodes have a predetermined relationship, an augmented knowledge graph is formed by a first computing device by extracting a second term from a domain corpus to form a term cluster linked with a respective node of the knowledge graph. The second term is associated with the first term of a respective node in the domain corpus while not meeting the predetermined relationship. A semantic feature between the second term and the associated first term is identified in the domain corpus and linked to the pair of the second term and the first term in the augmented knowledge graph. The augmented knowledge graph is useable by a second computing device, which may or may not be the same as the first computing device, to drive a conversation between a chatbot and user.

Abstract: Embodiments for replicating data in a disaggregated computing system. A memory pool is allocated, where the memory pool includes allocated memory elements at a first site and allocated memory elements at a second site. The allocated memory elements are mapped at the first site to the allocated memory elements at the second site. A replication operation is initiated to mirror data stored within the allocated memory elements at the first site to the allocated memory elements at the second site. The allocated memory elements at the first site are directly connected through an independent networking connection to the allocated memory elements at the second site such that the replication operation is processed exclusively through compute resources at the first site.