Abstract: Methods, systems and computer program products for multi-style text transformation are provided herein. A computer-implemented method includes selecting at least one set of style specifications for transforming at least a portion of input text. The at least one set of style specifications include one or more target writing style domains selected from a plurality of writing style domains, weights for each of the target writing style domains representing relative impact of the target writing style domains for transformation of at least a portion of the input text, and weights for each of a set of linguistic aspects for transformation of at least a portion of the input text. The computer-implemented method also includes generating one or more style-transformed output texts based at least in part on the at least one set of style specifications utilizing at least one unsupervised neural network.

Abstract: Methods, systems, and computer program products for unsupervised tunable stylized text transformations are provided herein. A computer-implemented method includes identifying amendable portions of input text by processing at least a portion of the input text using at least one neural network; determining stylistic text modifications to the amendable portions of the input text, the text modifications encompassing a set of stylistic parameters, wherein said determining comprises processing at least a portion of the set of stylistic parameters using at least one neural network; generating a stylized output set of text by transforming at least a portion of the input text, wherein said transforming comprises modifying at least one of the amendable portions of the input text via at least one of the stylistic text modifications encompassed by the set of stylistic parameters; and outputting the stylized output set of text to at least one user.

Abstract: Methods, systems and computer program products for multi-style text transformation are provided herein. A computer-implemented method includes obtaining input text and selecting a set of style specifications for transforming the input text. The set of style specifications include one or more target writing style domains selected from a plurality of writing style domains, weights for each of the target writing style domains representing relative impact of the target writing style domains for transformation of the input text, and weights for each of a set of linguistic aspects for transformation of the input text. The computer-implemented method also includes generating one or more style-transformed output texts based at least in part on the set of style specifications utilizing an unsupervised neural network.

Abstract: Methods, systems, and computer program products for generating concept images of human poses using machine learning models are provided herein. A computer-implemented method includes identifying one or more events from input data by applying a machine learning recognition model to the input data, wherein the identifying comprises (i) detecting multiple entities from the input data and (ii) determining one or more behavioral relationships among the multiple entities in the input data; generating, using a machine learning interpretability model and the identified events, one or more images illustrating one or more human poses related to the identified events; outputting the one or more generated images to at least one user; and updating the machine learning recognition model based at least in part on (i) the one or more generated images and (ii) input from the at least one user.

Abstract: Methods, systems, and computer program products for generating concept images of human poses using machine learning models are provided herein. A computer-implemented method includes identifying one or more events from input data by applying a machine learning recognition model to the input data, wherein the identifying comprises (i) detecting multiple entities from the input data and (ii) determining one or more behavioral relationships among the multiple entities in the input data; generating, using a machine learning interpretability model and the identified events, one or more images illustrating one or more human poses related to the identified events; outputting the one or more generated images to at least one user; and updating the machine learning recognition model based at least in part on (i) the one or more generated images and (ii) input from the at least one user.

Abstract: Methods, systems, and computer program products for unsupervised tunable stylized text transformations are provided herein. A computer-implemented method includes identifying stylistically amendable portions of input text by applying at least one neural network to the input text; determining stylistic text modifications to the amendable portions of the input text, the text modifications encompassing a set of stylistic parameters, wherein the determining comprises applying at least one neural network to the set of stylistic parameters; generating a stylized output set of text by transforming the input text, wherein the transforming comprises modifying at least one of the stylistically amendable portions of the input text via at least one of the stylistic text modifications encompassed by the set of stylistic parameters; and outputting the stylized output set of text to a user.

Abstract: Methods, systems, and computer program products for processing natural language analytics queries are provided herein.

Abstract: One embodiment provides a method, including: receiving a natural language query from a user; identifying a plurality of interpretations for interpreting the natural language query, wherein the plurality of interpretations are based upon at least one ambiguity in the received natural language query; generating, for each of the plurality of interpretations, a plurality of example queries; generating, for each of the interpretations, both (i) an answer to the received natural language query and (ii) an answer to each of the generated plurality of example queries; and providing, to the user, (i) the generated answer for each interpretation of the natural language query and (ii) a plurality of question/answer pairs for each of the identified plurality of interpretations that assists in disambiguating the ambiguity, wherein each question/answer pair comprises at least one of the generated plurality of example queries and the corresponding generated answer to the example query.

Abstract: Embodiments are disclosed for correcting a natural language interface database (NLIDB) system. The techniques include receiving feedback indicating that an answer provided in response to a question for an NLIDB system is inaccurate. The techniques further include finding an ontology element for a datastore of the NLIDB system that matches to the feedback. The techniques also include selecting candidate annotations for the NLIDB system based on the ontology element and a data type of the ontology element. Additionally, the techniques include generating a question-answer (QA) pair for each of the candidate annotations. Further, the techniques include adding one of the candidate annotations to annotations for a natural language query (NLQ) engine of the NLIDB system based on a client verification of the QA pair.

Abstract: Aspects of the present disclosure relate to automated ontology refinement based on query inputs and provided feedback. A query input is received for an ontology. Features of the query input are analyzed, wherein analyzation includes determining syntactical and semantic characteristics of the features of the query input. Based on the determined syntactical and semantic characteristics, ontological elements are classified for each feature of the query input. The ontological element for each feature of the query input is then compared to a set of ontological elements of the ontology. Based on the comparison, a response to the query input is received, along with a request for feedback regarding the response. Feedback is then received regarding the response. Based on the feedback, the ontology is analyzed to determine at least one deficiency of the ontology. The ontology is then refined to correct the at least one deficiency.

Abstract: Methods, systems and computer program products for multi-style text transformation are provided herein. A computer-implemented method includes obtaining input text and selecting a set of style specifications for transforming the input text. The set of style specifications include one or more target writing style domains selected from a plurality of writing style domains, weights for each of the target writing style domains representing relative impact of the target writing style domains for transformation of the input text, and weights for each of a set of linguistic aspects for transformation of the input text. The computer-implemented method also includes generating one or more style-transformed output texts based at least in part on the set of style specifications utilizing an unsupervised neural network.

Abstract: Text suggestions are generated. A document is received, and a portion score for at least one portion of the document is generated. A global assessment score for at least two portions of the document is also generated. A variation between the portion score and the global assessment score is calculated. It is determined that the variation is above a threshold variation, and at least one text change suggestion is generated.

Abstract: Techniques for the generation of variable natural language descriptions from structured data are disclosed including receiving input data and generating a first plurality of tuples based on the received input data. A first plurality of sentences and a corresponding second plurality of tuples are obtained from a data repository based on the first plurality of tuples. A second plurality of sentences is generated based on the second plurality of tuples, the first plurality of sentences, and the first plurality of tuples. A sentence is selected from the first plurality of sentences and the second plurality of sentences for each of the first plurality of tuples. At least one paragraph variation is generated where each paragraph variation is generated based on two or more of the selected sentences. The at least one paragraph variation is presented as a natural language description of the input data.

Abstract: One embodiment provides a method, including: deploying a machine learning model, wherein the deployed machine learning model is used in responding to queries from users; receiving, at the deployed machine learning model, input from a user; identifying a type of machine learning model attack corresponding to the received input; computing, responsive to receiving the input, a resiliency score of the machine learning model, wherein the resiliency score indicates resistance of the machine learning model against the identified type of attack; and performing an action responsive to the computed resiliency score.

Abstract: One embodiment provides a method, including: deploying a machine learning model, wherein the machine learning model is used in responding to queries from users; receiving, at the deployed machine learning model, input from at least one entity; determining that the at least one entity is an adversary attempting to retrain and/or steal the deployed machine learning model; and providing, in view of the determining that the at least one entity is an adversary, an altered response, wherein the altered response comprises at least one of: a response from a machine learning model other than the deployed machine learning model and a response from the deployed machine learning model altered with errors.

Abstract: Disclosed embodiments relate to a prefetcher for delinquent irregular loads. In one example, a processor includes a cache memory, fetch and decode circuitry to fetch and decode instructions from a memory; and execution circuitry including a binary translator (BT) to respond to the decoded instructions by storing a plurality of decoded instructions in a BT cache, identifying a delinquent irregular load (DIRRL) among the plurality of decoded instructions, determining whether the DIRRL is prefetchable, and, if so, generating a custom prefetcher to cause the processor to prefetch a region of instructions leading up to the prefetchable DIRRL.

Abstract: One embodiment provides a method, including: receiving, from a user, a natural language query; generating an ontology subgraph by mapping the natural language query to a domain ontology and filtering the domain ontology based upon entities within the natural language query; producing a knowledge graph from (i) the generated ontology subgraph and (ii) a set of documents related to the natural language query, wherein the producing comprises extracting triples from the set of documents and aggregating the extracted triples to form the knowledge graph; and providing, to the user, a response to the received natural language query, wherein the returning the response comprises querying the produced knowledge graph using the natural language query.

Abstract: One embodiment provides a method, including: utilizing at least one processor to execute computer code that performs the steps of: receiving a partially completed query request from a user, wherein the partially completed query request comprises at least one text string provided in a query field; mapping the at least one text string to at least one ontology element contained within at least one of a plurality of partitions in an ontology graph, the graph comprising (i) ontology elements represented as nodes and (ii) connections between ontology elements represented as edges, wherein each of the plurality of partitions corresponds to a subject area of a field and comprises ontology elements corresponding to concepts related to the subject area of the field; and generating, in view of the plurality of partitions, at least one suggestion for completing the query request to the user, wherein the at least one suggestion comprises a semantically relevant suggestion corresponding to the at least one text string prov

Abstract: Methods, systems, and computer program products for carrying out interactive dialog in natural language using an ontology are provided herein. A computer-implemented method includes generating one or more domain-driven interpretations of a natural language dialogue query provided by a user via utilization of a web ontology language; determining multiple structured base queries, from among a stored collection of structured queries, that correspond to the natural language dialogue query, in view of the one or more generated domain-driven interpretations; selecting one of the multiple determined structured base queries, based on one or more items of context information pertaining to the dialogue; automatically generating a response to the selected structured base query; and outputting the generated response to the user.

Abstract: Methods, systems, and computer program products for processing natural language analytics queries are provided herein.