Abstract: Systems and techniques that facilitate name-invariant graph neural representations for automated theorem proving are provided. In various embodiments, a system can access a set of first directed acyclic graphs respectively representing a conjecture and a set of axioms. In various aspects, the system can generate, via execution of at least one neural-guided automated theorem prover that independently processes the set of first directed acyclic graphs, a proof for the conjecture. In various instances, the at least one neural-guided automated theorem prover can leverage, for a node representing a non-logical symbol name present in more than one of the set of first directed acyclic graphs, a name-invariant learned embedding based on a second directed acyclic graph that is an aggregation of the set of first directed acyclic graphs.

Abstract: A system can comprise a memory that stores computer executable components, and a processor, operably coupled to the memory, that executes the computer executable components comprising: a linking component that associates one or more unmasked elements of the logical form with one or more corresponding structured knowledge elements of a knowledge base and a prediction component that predicts the one or more masked elements based on extended context of the corresponding structured knowledge elements of the knowledge base to generate one or more predicted elements. In an embodiment, the prediction component predicts the one or more masked elements based on scores of one or more candidate elements. In an embodiment, the system can determine one or more rules that describe the natural language text segment in terms of the structured knowledge elements and associated weights of the knowledge base paths.

Abstract: Methods, systems, and computer program products for extracting query-related temporal information from unstructured text documents are provided herein. A computer-implemented method includes obtaining at least one user query comprising one or more temporal components; converting at least a portion of the at least one user query into one or more logic form representations; mapping at least a portion of the one or more logic form representations to one or more portions of at least one source of unstructured text data; extracting temporal information, specific to the at least one user query, from one or more portions of the at least one source of unstructured text data based on the mapping; generating at least one response to the at least one user query based on the extracted temporal information; and performing one or more automated actions based on the at least one generated response.

Abstract: Systems and techniques that facilitate question answering via tailored knowledge induction are provided. In various embodiments, a system can access a natural language question. In various aspects, the system can identify an answer for the natural language question, based on a tailored knowledge graph iteratively generated from a set of structured sub-queries associated with the natural language question.

Abstract: A method implemented by a system for performing forward chaining using a property graph, the method includes generating, from an ontology, a simplified ontology that includes a set of sub-conditions connected through logical operators that are equivalent to the ontology. A state graph is created based on the simplified ontology. When a first assertion axiom (ABox) statement associated with the ontology is received, the first ABox statement is added to an instance graph based on the state graph. Inferred statements, if any, are derived based on connections between the instance graph and the state graph. The inferred statements are then stored with the first ABox statement. The state graph and the first ABox statement are stored in the property graph.

Abstract: Methods, systems, and computer program products for partitioning and parallel loading of property graphs with constraints are provided herein. A computer-implemented method includes obtaining graph-related input data and corresponding constraint data, wherein the graph-related input data and corresponding constraint data are at least one of user-defined and input data model-based; generating at least one in-memory graph based at least in part on processing at least a portion of the obtained graph-related input data; partitioning the at least one in-memory graph into two or more sub-graphs by processing the at least one in-memory graph using one or more polynomial time partition algorithms; and generating at least one property graph by allocating, at least a portion of the two or more partitioned sub-graphs which satisfy the obtained constraint data, to two or more threads that run in parallel.

Abstract: Methods, systems, and computer program products for extracting query-related temporal information from unstructured text documents are provided herein. A computer-implemented method includes obtaining at least one user query comprising one or more temporal components; converting at least a portion of the at least one user query into one or more logic form representations; mapping at least a portion of the one or more logic form representations to one or more portions of at least one source of unstructured text data; extracting temporal information, specific to the at least one user query, from one or more portions of the at least one source of unstructured text data based on the mapping; generating at least one response to the at least one user query based on the extracted temporal information; and performing one or more automated actions based on the at least one generated response.

Abstract: Methods, systems, and computer program products for partitioning and parallel loading of property graphs with constraints are provided herein. A computer-implemented method includes obtaining graph-related input data and corresponding constraint data, wherein the graph-related input data and corresponding constraint data are at least one of user-defined and input data model-based; generating at least one in-memory graph based at least in part on processing at least a portion of the obtained graph-related input data; partitioning the at least one in-memory graph into two or more sub-graphs by processing the at least one in-memory graph using one or more polynomial time partition algorithms; and generating at least one property graph by allocating, at least a portion of the two or more partitioned sub-graphs which satisfy the obtained constraint data, to two or more threads that run in parallel.

Abstract: In a method for deriving existential rules from knowledge graph data, a processor represents a knowledge graph using a geometric embedding. A processor transforms the geometric embedding to a syllogism logic representation using a geometric relationship. And a processor derives existential rules using standard transformation rules present in the syllogism logic representation.

Abstract: Methods, systems and computer program products for query processing are provided herein. A computer-implemented method includes receiving a first query from a user, determining whether the first query is capable of being answered using symbolic reasoning performed on data of a symbolic knowledge base, and executing the symbolic reasoning to generate a first query answer in response to a determination that the first query is capable of being answered using the symbolic reasoning. Axioms are extracted from a plurality of documents when it is determined that a second query is not capable of being answered using the symbolic reasoning. The method further includes determining whether the axioms are consistent with the symbolic knowledge base, and generating a second query answer based on the axioms in response to a determination that the one or more axioms are consistent with the symbolic knowledge base.

Abstract: Methods, systems, and computer program products for table recognition in PDF documents are provided herein. A computer-implemented method includes discretizing one or more contiguous areas of a PDF document; identifying one or more white-space separator lines within the one or more discretized contiguous areas of the PDF document; detecting one or more candidate table regions within the one or more discretized contiguous areas of the PDF document by clustering the one or more white-space separator lines into one or more grids; and outputting at least one of the candidate table regions as a finalized table in accordance with scores assigned to each of the one or more candidate table regions based on (i) border information and (ii) cell structure information.

Abstract: Methods, systems and computer program products for query processing are provided herein. A computer-implemented method includes receiving a first query from a user, determining whether the first query is capable of being answered using symbolic reasoning performed on data of a symbolic knowledge base, and executing the symbolic reasoning to generate a first query answer in response to a determination that the first query is capable of being answered using the symbolic reasoning. Axioms are extracted from a plurality of documents when it is determined that a second query is not capable of being answered using the symbolic reasoning. The method further includes determining whether the axioms are consistent with the symbolic knowledge base, and generating a second query answer based on the axioms in response to a determination that the one or more axioms are consistent with the symbolic knowledge base.

Abstract: Methods, systems, and computer program products for table recognition in PDF documents are provided herein. A computer-implemented method includes discretizing one or more contiguous areas of a PDF document; identifying one or more white-space separator lines within the one or more discretized contiguous areas of the PDF document; detecting one or more candidate table regions within the one or more discretized contiguous areas of the PDF document by clustering the one or more white-space separator lines into one or more grids; and outputting at least one of the candidate table regions as a finalized table in accordance with scores assigned to each of the one or more candidate table regions based on (i) border information and (ii) cell structure information.

Abstract: Identification of an intent of a conversation can be useful for real-time or post-processing purposes. According to example embodiments, a method, and corresponding apparatus of identifying at least one intent-bearing utterance in a conversation, comprises determining at least one feature for each utterance among a subset of utterances of the conversation; classifying each utterance among the subset of utterances, using a classifier, as an intent classification or a non-intent classification based at least in part on a subset of the at least one determined feature; and selecting at least one utterance, with intent classification, as an intent-bearing utterance based at least in part on classification results by the classifier. Through identification of an intent bearing utterance, a call center for example, can provide improved service for callers through, for example, more effective directing of a call to a live agent.

Abstract: Labeling a call, for instance by identifying an intent (i.e., the reason why the caller has called into the call center), of a caller in a conversation between a caller and an agent is a useful task for efficient customer relationship management (CRM). In an embodiment, a method of labeling sentences for presentation to a human can include selecting an intent bearing excerpt from sentences, presenting the intent bearing excerpt to the human, and enabling the human to apply a label to each sentence based on the presentation of the intent bearing excerpt. The method can reduce a manual labeling budget while increasing the accuracy of labeling models based on manual labeling.

Abstract: Identification of an intent of a conversation can be useful for real-time or post-processing purposes. According to example embodiments, a method, and corresponding apparatus of identifying at least one intent-bearing utterance in a conversation, comprises determining at least one feature for each utterance among a subset of utterances of the conversation; classifying each utterance among the subset of utterances, using a classifier, as an intent classification or a non-intent classification based at least in part on a subset of the at least one determined feature; and selecting at least one utterance, with intent classification, as an intent-bearing utterance based at least in part on classification results by the classifier. Through identification of an intent bearing utterance, a call center for example, can provide improved service for callers through, for example, more effective directing of a call to a live agent.