International Business Machines Corporation

University of Illinois

Airbnb, Inc.

Yu Deng

Ruchi Mahindru

Soumitra Sarkar

Jenny S Li

Rafah A Hosn

Andrzej P Kochut

Hidayatullah Habeebullah Shaikh

Murthy V Devarakonda

Liangzhao Zeng

Harigovind Venkatraj Ramasamy

Long Wang

Anca Sailer

Jonathan Paul Munson

Michael Reuben Head

Al Chakra

Randy Allan Rendahl

Nithya Rajamani

Alexei A Karve

Theresa Y Tai

Rick A Hamilton, Ii

Christopher J Dawson

Lisa Seacat DeLuca

Norbert George Vogl

Lingfei Wu

Kaoutar El Maghraoui

Maja Vukovic

Alla Segal

Shu Tao

Lakshminarayanan Renganarayana

Sinem Guven Kaya

Rajarshi Haldar

Matthew R Koozer

Rongda Zhu

Russell W Bergs

John Alan Bivens

Min Li

Mahesh Viswanathan

Richard Edwin Harper

Alfio Massimiliano Gliozzo

Anup Kalia

Jin Xiao

Md Faisal Mahbub Chowdhury

Gaetano Rossiello

Nicolas Rodolfo Fauceglia

Nandana Sampath Mihindukulasooriya

Angel E Tomala-Reyes

Quang C Duong

Tara Lynn Astigarraga

Roman Vaculin

Sheng Hua Bao

Srikanth Govindaraj Tamilselvam

Minkyong Kim

Jim Alain Laredo

Charles Otto Schulz

Salman Abdul Baset

Chang-Shing Perng

Peter Martin Schwarz

Daniela Rosu

Qi Hu

Thao Ngoc Nguyen

Bruce David D'Amora

Julia Elizabeth Rice

John Joseph Bird

Grzegorz Michal Swirszcz

Sarthak Dash

Simon J Kofkin-Hansen

Jens Rathgeber

Hong Lin Guo

Julia Constanze Hockenmaier

Hui Kang

Cuong Manh Pham

Tarek Sakakini

Meng Jiang

Qingkai Zeng

Wenhao Yu

Xinyu Que

Rahul D Sharnagat

Zhiyu Chen

Theodor Razvan Ionescu

Christopher Moss

Richard Christopher Smith

Abhas Bodas

Computer-implemented techniques for unsupervised event extraction are provided. In one instance, a computer implemented method can include parsing, by a system operatively coupled to a processor, unstructured text comprising event information to identify candidate event components. The computer implemented method can further include employing, by the system, one or more unsupervised machine learning techniques to generate structured event information defining events represented in the unstructured text based on the candidate event components.

Unsupervised event extraction

Techniques facilitating anomaly detection and root cause analysis using distributed trace data. In one example, a system can comprise a processor that executes computer executable components stored in memory. The computer executable components comprise: a preprocessing component; and a monitor component. The preprocessing component can generate a trace frame comprising a vectorized representation of textual trace data produced by microservices of a microservice application. The monitor component can identify a state of the microservice application using the trace frame.

Learning from distributed traces for anomaly detection and root cause analysis

An approach for a non-factoid question answering framework across tasks and domains may be provided. The approach may include training a multi-task joint learning model in a general domain. The approach may also include initializing the multi-task joint learning model in a specific target domain. The approach may include tuning the joint learning model in the target domain. The approach may include determining which task of the multiple tasks is more difficult for the multi-task joint learning model to learn. The approach may also include dynamically adjusting the weights of the multi-task joint learning model, allowing the model to concentrate on learning the more difficult learning task.

Non-factoid question answering across tasks and domains

Systems, devices, computer-implemented methods, and/or computer program products that facilitate software vulnerability analysis using relationship data extracted from disparate package-related sources. In one example, a system can comprise a processor that executes computer executable components stored in memory. The computer executable components can comprise a knowledge induction component and a vulnerability component. The knowledge induction component can populate a package ontology for a range of packages with relationship data extracted from a plurality of disparate package-related sources. The vulnerability component can identify an implicit vulnerability impacting the range of packages using the package ontology and a vulnerability record regarding an explicit vulnerability for a package within the range of packages.

Traversing software components and dependencies for vulnerability analysis

Systems, computer-implemented methods, and computer program products that can facilitate extraction of named entities from document data to support automation applications are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise an entity extraction component that extracts, using a first machine learning process, a first data entity and a second data entity from document data indicative of a textual information. The computer executable components can further comprise a relation extraction component that determines, using a second machine learning process, a relation between the first data entity and the second data entity to generate a knowledge data graph used to execute an application associated with natural language processing for the document data.

Extraction of named entities from document data to support automation applications

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.

Graph-based event schema induction for information retrieval

An example operation may include one or more receiving notifications from one or more monitoring agents, each notification comprising a monitoring agent identifier, one or more configuration changes, and a timestamp corresponding to each configuration change, identifying incremental configuration changes that may require a disaster recovery retest, requesting a partial disaster recovery retest comprising the incremental configuration changes, the partial disaster recovery retest providing test coverage for a subset of a full disaster recovery test plan, and providing a request to a blockchain network to store information for the received notifications to a shared ledger of the blockchain network.

Database optimized disaster recovery orchestrator

Usage information of a user for a plurality of computing devices is identified. A usage pattern for each computing device of the plurality of computing devices of the user is developed based on the identified usage information of the user. An indication of the user accessing an application on a first computing device of the plurality of computing devices is received. The application requires one or more credentials for an authentication process associated with the application. A determination is made whether the user accessing the application using the first computing device is following the developed usage pattern of the user. Responsive to determining that the user accessing the application using the first computing device is not following developed usage pattern of the user, the authentication process associated with the application is interrupted.

Multi-factor authentication via multiple devices

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.

Discovering ranked domain relevant terms using knowledge

Systems, computer-implemented methods, and computer program products to facilitate query recommendation are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise an ontology component that can generate an ontology based on unstructured data of a description of an application programming interface. The computer executable components can further comprise a reasoner component that can identify one or more terms of the ontology that correspond semantically to a term of a query.

Query recommendation to locate an application programming interface

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.

Automated evaluation of information retrieval

A base query having a plurality of base query terms is obtained. A plurality of problem log files are accessed. Words, contained in a corpus vocabulary, are extracted from the plurality of problem log files. Based on the words extracted from the plurality of problem log files, a first expanded query is generated from the base query. The corpus is queried, via a query engine and a corpus index, with a second expanded query related to the first expanded query.

Log-aided automatic query expansion approach based on topic modeling

A method, system and computer program product are disclosed for searching for data. In one embodiment, the invention provides a method comprising identifying a query and a search scope including a set of specified entities; and for each of these entities, estimating a number of documents that would be identified in a search through the entity to answer the query. On the basis of this estimating, a subset of the entities is formed. The query and this subset of entities are sent to a search engine to search the subset of entities to answer the query. In one embodiment, the estimating includes collecting statistical information from queries to build up a historical cache using heuristics or machine learning techniques, wherein the query includes a key word and a scope, and the historical cache contains a maximum number of returned results for an entity given the queries executed.

Using historical information to improve search across heterogeneous indices

In an approach for providing reading insight and notification on a URL with unfamiliar content for a user, a processor parses a web page to identify a URL. The URL references a subsequent web page. Prior to receiving a user interaction with the URL, a processor prefetches content of the subsequent web page. A processor determines a content domain of the prefetched content, the content domain being a summary of the prefetched content. A processor compares the content domain to a user profile, wherein the use profile is based, at least in part, on a browsing history of a user. A processor determines that the content domain is not in alignment to the user profile. A processor presents a notification to the user.

Providing reading insight on URLs with unfamiliar content

Growing community of inventors

Yorktown Heights, NY, United States of America

Yu Deng