International Business Machines Corporation

Charles Arthur Jochim

Elizabeth Daly

Radu Marinescu

Francesca Bonin

Akihiro Kishimoto

Emanuele Ragnoli

John Erik Wittern

Yassine Lassoued

Pierpaolo Tommasi

Fearghal O'Donncha

Yufang Hou

Vanessa Lopez Garcia

Alice-Maria Marascu

Lea Deleris

Stephane Deparis

Carlos A Alzate Perez

Ying Liu

Beat Buesser

Thanh Lam Hoang

Noam Slonim

Ranit Aharonov

Killian Levacher

Campbell D Watson

Ngoc Minh Tran

Debasis Ganguly

Roy N Bar-Haim

Orith Toledo-Ronen

Bogdan Eugen Sacaleanu

Martin Gleize

Alon Halfon

Amir Menczel

Alice Marascu

Fearghal ODonncha

Embodiments for assisting pronunciation correction are described. A representation of a user pronunciation of an utterance is received. A representation of a target pronunciation of the utterance is identified. The representation of the user pronunciation of the utterance is compared to the representation of the target pronunciation of the utterance. A recommendation associated with correcting the user pronunciation of the utterance is generated based on the comparing of the representation of the user pronunciation of the utterance to the representation of the target pronunciation of the utterance and information associated with the user.

Methods and systems for assisting pronunciation correction

Systems, computer-implemented methods and/or computer program products that facilitate answering questions that involve mathematical computations are provided. In one embodiment, a computer-implemented method comprises: transforming, by a system operatively coupled to a processor, a natural language query into a first logical representation and extrinsic knowledge into a second logical representation relevant to the natural language query; merging, by the system, the first logical representation and the second logical representation into a third logical representation; and generating, by the system, answers for the natural language query based on processing of the third logical representation.

Facilitating answering questions involving reasoning over quantitative information

An application automatically composed using natural language processing. A natural language input comprising one or more application requirements is received via an interface. The natural language input is parsed to extract one or more chunks, each chunk representing one of the application requirements, and at least one of the chunks representing at least one of one or more main functionalities described by the application requirements. A coarse architecture logically arranging the main functionalities to satisfy the application requirements is inferred according to the chunks. Existing assets corresponding to the chunks are identified, each asset associated with at least one of the main functionalities. The identified assets are assembled according to the coarse architecture. The assembled assets are deployed as an application.

Automated application composer with natural language processing

An information retrieval response may be augmented, based upon a query, with a plurality of selected causality data relating to the query. The information retrieval response may be generated from an information retrieval system.

Providing causality augmented information responses in a computing environment

A method including: generating, from a text corpus, a lexicon of unigrams and bigrams comprising an embedding for each of said unigrams and bigrams; training a machine learning classifier on a training set comprising a subset of said lexicon, wherein each of said unigrams and bigrams in said subset has a sentiment label; applying said machine learning classifier to said lexicon, to (i) predict a sentiment of each of said unigrams and bigrams, and (ii) update said lexicon with the predicted sentiments; and performing statistical analysis on said updated lexicon, to extract one or more sentiment composition lexicons, wherein each of said one or more sentiment composition lexicons is associated with a sentiment composition class.

Learning sentiment composition from sentiment lexicons

A computer system, method, and computer readable product are provided for cognitive initialization of large-scale advection-diffusion models. In various embodiments, parameters are identified for configuring an advection-diffusion model to be run. Then a natural language processing search is conducted for these parameters in relevant literature to find corresponding numerical values. These search results are compared, and values for the parameters are set for the advection-diffusion model, and the model is run.

Cognitive initialization of large-scale advection-diffusion models

Embodiments for co-reference resolution and entity linking from unstructured text data by a processor. Semantic co-references and mentions of one or more entities may be resolved occurring in unstructured text data by linking the one or more entities using a domain knowledge ontology.

Co-reference resolution and entity linking

Embodiments for discovery and analysis of interpersonal relationships from a collection of unstructured text data by a processor. A relationship between one or more entities and extracted text data from a plurality of unstructured text data may be identified such that the relationship includes a sentiment of the relationship, a type of relationship, temporal information, or a combination thereof. The one or more entities may be associated with a knowledge graph based on an ontology of concepts representing a domain knowledge. The extracted information and the identified relationship may be automatically aggregated into a multi-graph representation.

Discovery, characterization, and analysis of interpersonal relationships extracted from unstructured text data

Embodiments for analyzing images by one or more processors are described. An image is received. An object appearing in the image is detected. A scene graph is generated for the object. At least one transformational matrix is determined for the object. The at least one transformational matrix is associated with rendering the object as the object appears in the image based on the scene graph.

Methods and systems for analyzing images utilizing scene graphs

A distributed computer system includes a distributed processor, a distributed memory, and a simulation engine (SE). The SE includes a simulation I/O coupler that links a first variable of a first simulation model I/O data structure to a second variable of a second simulation model I/O data structure. The SE includes a natural language processing system that extracts a first variable description associated with the first variable, determines similar character strings to the first variable description from an information corpus, and ranks the determined character strings based upon similarity to the first variable description. The SE links the first variable to the second variable if the rank of an equal character string to the second variable description is greater than a rank threshold. The SE may augment the simulation model I/O data structures by writing a value of the first variable to a value of the second variable, or visa versa.

Data analysis for automated coupling of simulation models

A method for automatically extracting claim candidates from complex sentences includes providing a parse tree of a text sample to be analyzed, disassembling the parse tree into a set of basic meaning-bearing clauses, assembling clauses of the set of basic clauses into a set of complex coherent statements based on permissible syntactic structures, testing the complex statements and discarding those statements that are not coherent when considered alone, discarding those complex statements that either do not provide additional information about a subject, or are too complex, removing information from a complex statement that provides supportive details about the subject, and discarding statements that restrict their subject, so that the subject cannot be generalized encompass a broader subject.

Rule-based syntactic approach to claim boundary detection in complex sentences

Growing community of inventors

Dublin, Ireland

Charles Arthur Jochim