International Business Machines Corporation

Nuance Communications, Inc.

L Venkata Subramaniam

Tanveer Afzal Faruquie

Hima Prasad Karanam

Mukesh Kumar Mohania

Snigdha Chaturvedi

Marvin Mendelssohn

Sameep Mehta

Nitendra Rajput

Ashish Verma

Shourya Roy

Chalapathy Venkata Neti

Girish Venkatachaliah

Shajith I Mohamed

Udit Sharma

Sumit Neelam

Sachindra Joshi

Hironori Takeuchi

Tetsuya Nasukawa

Raghuram Krishnapuram

Dinesh Garg

Saswati Dana

Tanveer A Faruquie

Santosh Srivastava

Vijay Ekambaram

Kuntal Dey

Seema Nagar

Andrew William Senior

Sriram Kolinjivadi Padmanabhan

Amit Anil Nanavati

Sougata Mukherjea

Charles Daniel Wolfson

Krishna Kummamuru

Manoj Kumar Agarwal

Himanshu Gupta

Sumit Negi

Vikas V Joshi

Sumit Bhatia

Sreyash Kenkre

Saneem Ahmed Chemmengath

Sankar Basu

Mohan Nagraj Dani

Pavan Kapanipathi Bangalore

Alexander Gray

Salim E Roukos

Nisanth Maliakkal Simon

Dinesh Khandelwal

G P Shrivatsa Bhargav

Bhupesh S Chawda

Ganesh Ramakrishnan

Angel Marie Smith

Chawda Bhupesh Shyamsundar

Oliver Markus Vogel

Kanika Narang

Mrinmaya Sachan

Diwakar Punjani

Deepak S Padmanaban

Tanveer Atzal Faruquie

Raguhuram Krishnapuram

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 zero-shot entity linking based on symbolic information are provided herein. A computer-implemented method includes obtaining a knowledge graph comprising a set of entities and a training dataset comprising text samples for at least a subset of the entities in the knowledge graph; training a machine learning model to map an entity mention substring of a given sample of text to one corresponding entity in the set of entities, wherein the machine learning model is trained using a multi-task machine learning framework using symbolic information extracted from the knowledge graph; and mapping an entity mention substring of a new sample of text to one of the entities in the set using the trained machine learning model.

Zero-shot entity linking based on symbolic information

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 explaining cross domain model predictions are provided herein. A computer-implemented method includes providing a test data point to a domain adaptation model to obtain a prediction, wherein the domain adaptation model is trained on a set of labeled data points and a set of unlabeled data points. The method includes generating a task specific explanation for the prediction that includes one or more data points from among the sets that satisfy a threshold score for influencing the prediction. Additionally, the method includes generating a domain invariant explanation for the prediction. The domain variation explanation is generated by ranking pairs of data points based on a statistical similarity to the test data point, wherein each pair includes a data point from the set of labeled data points and a data point from the set of unlabeled data points.

Explaining cross domain model predictions

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

One embodiment provides a method, including utilizing at least one processor to execute computer code that performs the steps of: receiving, from a user, one or more keywords, wherein the one or more keywords identify, within a social media data set, a subset of social media data; determining, based on social media statistical information, an estimated volume of the subset of the social media data; determining, based on the social media statistical information, an estimated relevance of the subset of social media data to the user; and updating the one or more keywords, to improve the estimated volume and estimated relevance. Other aspects are described and claimed.

Keyword based data crawling

Computer program products and systems are provided for mining for sub-patterns within a text data set. The embodiments facilitate finding a set of N frequently occurring sub-patterns within the data set, extracting the N sub-patterns from the data set, and clustering the extracted sub-patterns into K groups, where each extracted sub-pattern is placed within the same group with other extracted sub-patterns based upon a distance value D that determines a degree of similarity between the sub-pattern and every other sub-pattern within the same group.

Automatically mining patterns for rule based data standardization systems

The present invention relates to data cleansing, and in particular performing the semantic standardization process within a database before the transform portion of the extract-transform-load (ETL) process. Provided are a method, system and computer program product for standardizing data within a database engine, configuring the standardization function to determine at least one standardized value for at least one data value by applying the standardization table in a context of at least one data value, receiving a database query identifying the standardization function, at least one database value and the context of the data, and invoking the standardization function.

In-querying data cleansing with semantic standardization

Methods and arrangements for keyword refinement and enhancement. There is received an initial keyword list comprising one or more keywords. Information is harvested from one or more information feeds, and an item is ascertained from the harvested information. One or more keywords from the initial keyword list are associated with the item. One or more new keywords are developed based on the associating of one or more keywords from the initial keyword list with the item. Other variants and embodiments are broadly contemplated herein.

Keyword refinement in temporally evolving online media

Systems and methods for identifying entities sharing a temporal pattern using bipartite graphs are described. In one embodiment, a method includes identifying a temporal pattern in a sequence of bipartite graphs for a sequence of records involving two entity types, where records of the sequence of bipartite graphs vary according to time. An embodiment may color code the edges between entity types in the sequence of bipartite graphs according to the at least one temporal pattern identified (e.g., increasing sales between a business representative and a customer). An embodiment may therefore identify a time-based relationship between at least two entities according to the coded edges. Given the identification of entities having a time-based relationships, groups of these entities may be identified and trends may be derived therefrom (e.g., increasing sales for business units of a particular geographic region).

Systems and methods for discovering temporal patterns in time variant bipartite graphs

Systems and associated methods for address standardization and applications related thereto are described. Embodiments exploit a common context in a taxonomy and a given address to detect and correct deviations in the address. Embodiments establish a possible path from a root of the taxonomy to a leaf in the taxonomy that can possibly generate a given address. Given a new address, embodiments use complete addresses, and/or segments or elements thereof, to compute the representations of the elements and find a closest matching leaf in the taxonomy. Embodiments then traverse the path to a root node to detect the agreement and disagreement between the path and the address entry. Taxonomical structured is thus used to detect, segregate and standardize the expected fields.

Systems and methods for standardization and de-duplication of addresses using taxonomy

Techniques, systems, and articles of manufacture for determining related data points from multi-modal inputs. A method includes collecting multiple items of multi-modal data comprising at least one dimension from multiple data sources, wherein said at least one dimension comprises a geographic dimension, a temporal dimension and/or an event-related dimension, determining a window of relevance for each of the multiple items of multi-modal data with respect to the at least one dimension, and identifying two or more of the multiple items of multi-modal data as related, by determining an overlap of the window of relevance corresponding to each of the two or more items of multi-modal data with respect to the at least one dimension.

Determining related data points from multi-modal inputs

Techniques, systems, and articles of manufacture for processing spatial joins using a MapReduce framework. A method includes partitioning a spatial data domain based on a distribution of spatial data objects across multiple nodes of a cluster of machines, defining at least one operation to be performed on the partitioned spatial data domain based on one or more predicates of a query, and executing the at least one defined operation on the partitioned spatial data domain to determine a response to the query.

Processing spatial joins using a mapreduce framework

A method, system and a computer program product for determining resources allocation in a distributed computing environment. An embodiment may include identifying resources in a distributed computing environment, computing provisioning parameters, computing configuration parameters and quantifying service parameters in response to a set of service level agreements (SLA). The embodiment may further include iteratively computing a completion time required for completion of the assigned task and a cost. Embodiments may further include computing an optimal resources configuration and computing at least one of an optimal completion time and an optimal cost corresponding to the optimal resources configuration. Embodiments may further include dynamically modifying the optimal resources configuration in response to at least one change in at least one of provisioning parameters, computing parameters and quantifying service parameters.

Resources management in distributed computing environment

Growing community of inventors

Gurgaon, India

L Venkata Subramaniam