International Business Machines Corporation

Nuance Communications, Inc.

Shajith I Mohamed

L Venkata Subramaniam

Hima Prasad Karanam

Sumit Neelam

Udit Sharma

Ashish Verma

Karthik Visweswariah

Nandakishore Kambhatla

Debapriyo Majumdar

Sugata Ghosal

Om Dadaji Deshmukh

Rose Catherine Kanjirathinkal

Anup Kumar Ghosh

Asidhara Lahiri

Santosh Srivastava

Sachindra Joshi

Soumitra Sarkar

Shivakumar Vaithyanathan

Rafah A Hosn

Etienne Marcheret

Rajasekar Krishnamurthy

Prithviraj Sen

Kenneth W Church

Sumit Bhatia

Douglas Ronald Burdick

Jeffrey N Marcus

Vijil Enara Chenthamarakshan

Alexandre Valentinovich Evfimievski

Prasanta Kumar Ghosh

Marina Danilevsky Hailpern

Wei Cheng

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.

Question answering via tailored knowledge induction

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.

Extracting query-related temporal information from unstructured text documents

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.

Partitioning and parallel loading of property graphs with constraints

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.

System and method for approximate reasoning using ontologies and unstructured data

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.

Table recognition in portable document format documents

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.

System and method for identification of intent segment(s) in caller-agent conversations

Embodiments of the present invention relate to an approach for reusing information/knowledge. Specifically, embodiments of the present invention provide an approach for retrieving previously stored data to satisfy queries (e.g., jobs/tickets) for solutions to problems while maintaining privacy/security of the data as well as ensuring the quality of the results. In a typical embodiment, a query for a solution to a problem is received and details are extracted therefrom. Using the details, a search is performed on a set of data stored in at least one computer storage device. Based on the search, a set of results will be generated and classified into a set of categories. In any event, the quality of each of the set of results will be assessed based on the usefulness of the set of results.

Computer-implemented information reuse

A system and method are described for generating semantically similar sentences for a statistical language model. A semantic class generator determines for each word in an input utterance a set of corresponding semantically similar words. A sentence generator computes a set of candidate sentences each containing at most one member from each set of semantically similar words. A sentence verifier grammatically tests each candidate sentence to determine a set of grammatically correct sentences semantically similar to the input utterance. Also note that the generated semantically similar sentences are not restricted to be selected from an existing sentence database.

System and a method for generating semantically similar sentences for building a robust SLM

A method, an apparatus and an article of manufacture for automatic speech recognition. The method includes obtaining at least one language model word and at least one rule-based grammar word, determining an acoustic similarity of at least one pair of language model word and rule-based grammar word, and increasing a transition cost to the at least one language model word based on the acoustic similarity of the at least one language model word with the at least one rule-based grammar word to generate a modified language model for automatic speech recognition.

Automatic speech and concept recognition

A method, a system and a computer program product for analyzing a document are disclosed. In response to receiving the document, the document is partitioned into a plurality of segments using a set of pre-defined attributes. The plurality of segments of the document is mapped with corresponding segments of at least one template selected from a set of stored templates. A first template from the set of stored templates is selected and a group of segments in the first template is identified by computing at least one of a structural similarity and a textual similarity associated with the group of segments compared with the plurality of segments of the document. A subset of segments from the group of segments is aligned with corresponding segments from the plurality of segments of the document. A set of scores is computed using a set of pre-defined criteria, in response to the mapping. The document is analyzed based on the computed set of scores.

Analyzing documents using stored templates

Growing community of inventors

Bengaluru, India

Shajith I Mohamed