International Business Machines Corporation

Chris M Mwarabu

Corville O Allen

Roberto Delima

David Contreras

Kandhan Sekar

Krishna Mahajan

Kevin Glynn Paterson

Christopher Thomas Gloe

Michael John Fork

Theodore J L Shrader

Michael Britt

Thomas P Pitzen

Thomas Hay Rogers

Joshua Cason

A phrase that includes a trigger word that modifies a meaning within the phrase is received. The trigger word is identified. The words of the phrase that are modified by the trigger word are identified by analyzing features of the phrase that link the trigger word to other words. The phrase is interpreted by modifying the second subset of words according to the modification of the trigger word.

Contextual span framework

A method, system, and computer program product for using a natural language processor is disclosed. Included are importing highlighted and non-highlighted training text each including training nodes, one-hot encoding the training text, training a projection model using the training text, processing the highlighted training text using the projection model, and training a classifier model using the highlighted processed training text. Also included are importing new text including new nodes, one-hot encoding the new text, processing the new text using the projection model, and determining, using the classifier model, whether one of the new nodes is in a sought-after class.

Deep learning approach to computing spans

Aspects of the present disclosure relate to identifying semantic relationships. Natural language content is received. A part of speech is determined for respective terms within the natural language content. A semantic type is determined for each of two or more terms within the natural language content. A parse tree representation containing a plurality of nodes is then generated based on the natural language content, each of the plurality of nodes corresponding to at least one term within the natural language content, wherein visual characteristics of respective nodes of the plurality of nodes within the parse tree representation depend on the part of speech and semantic type of the respective terms. A bounding box identifying a semantic relationship is then generated around a set of nodes on the parse tree representation, the set of nodes including the two or more terms.

Identifying semantic relationships using visual recognition

Aspects of the present disclosure relate to identifying spans within unstructured electronic text. Natural language content is received. A part of speech and slot name of each word within the natural language content is identified. A parse tree representation is then generated based on the natural language content, wherein visual characteristics of each node of a plurality of nodes within the parse tree representation depend on the part of speech and slot name of each word. A bounding box identifying a span category is then generated around a set of nodes on the parse tree representation by a machine learning model.

Identifying spans using visual recognition

A phrase may be received that includes a plurality of tokens in a natural language format. A plurality of levels relating to dependencies between tokens of the plurality of tokens within the phrase is determined. A matrix structure is generated for the phrase. The matrix structure utilizes a plurality of rows and a plurality of columns to store data of the phrase. The plurality of rows and the plurality of columns each indicate one of an order of tokens of the plurality of tokens or levels of the plurality of levels.

Natural language processing matrices

In an embodiment, if a number of segments of a video in a buffer after a buffer position is less than a play threshold, then a first plurality of segments is sent into the buffer in time order; and if the number of the segments in the buffer at the buffer position is not less than the play threshold, a second plurality of segments is sent to the buffer in popularity order, wherein the second plurality of segments are stored into the buffer in time order.

Switching between time order and popularity order sending of video segments

In an embodiment, a guest operating system receives first host network information that identifies a host virtual network adapter. The first host network information uniquely identifies the host virtual network adapter. The guest operating system sends a first frame that comprises the first host network information to a guest virtual network adapter. The guest virtual network adapter sends the first frame to the host virtual network adapter. The guest operating system receives second host network information that identifies the host virtual network adapter. The second host network information uniquely identifies the host virtual network adapter. The guest operating system sends a second frame that comprises the second host network information to the guest virtual network adapter. The guest virtual network adapter sends the second frame to the host virtual network adapter identified by the second host network information in the second frame.

Growing community of inventors

Cary, NC, United States of America

Chris M Mwarabu