Salesforce, Inc.

Narrative Science Inc.

Nathan William Krapf

Nathan Drew Nichols

Alexander Rudolf Sippel

Bo He

Brendan Robert Gimby

Mauro Eduardo Ignacio Mujica-Parodi, Iii

Clayton Nicholas Norris

Michael Tien Thinh Pham

Stephen Emmanuel Hudson

Michael Justin Smathers

Matthew Lloyd Trahan

Natural language generation technology is disclosed that applies artificial intelligence to structured data to determine content for expression in natural language narratives that describe the structured data. A graph data structure is employed, where the graph data structure comprises a plurality of nodes. The nodes (1) represent corresponding intents so that different nodes represent different corresponding intents, (2) are associated with corresponding analytics for execution to evaluate a given node's corresponding intent and generate a result that represents an evaluation of that node's corresponding intent, and (3) are associated with one or more links with one or more of the nodes to define relationships among the intents. A processor traverses the graph data structure based on defined criteria and a plurality of the links to (1) choose which nodes are to be evaluated and (2) determine content for expression in the narratives based on execution of the chosen nodes' corresponding analytics against the structured data.

Applied artificial intelligence technology for natural language generation using a graph data structure

Natural language generation technology is disclosed that applies artificial intelligence to structured data to determine content for expression in natural language narratives that describe the structured data. A graph data structure is employed, where the graph data structure comprises a plurality of nodes. Each of a plurality of the nodes (1) represents a corresponding intent so that a plurality of different nodes represent different corresponding intents and (2) is associated with one or more links to one or more of the nodes to define relationships among the intents. A processor executes chooser code, structurer code, and realizer code to generate the natural language narratives. The chooser code determines content for expression in a natural language narrative based on a traversal of the graph data structure based on defined criteria and a plurality of the links, wherein the traversal operates to choose a plurality of the nodes for evaluation with respect to the structured data to derive content for expression in that natural language narrative.

Applied artificial intelligence technology for natural language generation using a graph data structure in combination with chooser code, structurer code, and realizer code

Systems and methods are disclosed for integrating NLG-based natural language narrative story generation with story sharing. A processor can (1) generate a plurality of natural language narrative stories based on a plurality of semantic source models for the natural language narrative stories, (2) analyze the semantic source models to determine a plurality of users to whom the natural language narrative stories that are generated from the analyzed semantic source models are to be shared, and (3) share the generated natural language narrative stories with their determined users. In this fashion, stories can be posted to user-customized newsfeeds in a manner that can more reliably capture stories that are of interest to the users.

Applied artificial intelligence technology for integrating natural language narrative generation with newsfeeds

Natural language generation technology is disclosed that applies artificial intelligence to structured data to determine content for expression in natural language narratives that describe the structured data. A graph data structure is employed, where the graph data structure comprises a plurality of nodes. Each of a plurality of the nodes (1) represents a corresponding intent so that a plurality of different nodes represent different corresponding intents and (2) is associated with one or more links to one or more of the nodes to define relationships among the intents. A processor executes chooser code based on a plurality of operating rules and/or parameters that control how the chooser code traverses the graph data structure to determine which of the nodes to use for content to be expressed in the natural language narratives, wherein the operating rules and/or parameters are configurable to change strategies for choosing which nodes are used for the content to be expressed in the natural language narratives.

Applied artificial intelligence technology for natural language generation using a graph data structure and configurable chooser code

Natural language generation technology is disclosed that applies artificial intelligence to structured data to determine content for expression in natural language narratives that describe the structured data. A story graph is employed, where the story graph comprises a plurality of items of content to be expressed in a natural language narrative. A processor executes code corresponding to any of a plurality of structurers that organize the items of content into different story outlines from which the natural language narratives are generated, wherein the different structurers comprise different operating rules and/or parameters that implement different strategies for organizing the items of content into the story outlines.

Applied artificial intelligence technology for natural language generation using a story graph and different structurers

Disclosed herein are example embodiments of an improved narrative generation system where an analysis service that executes data analysis logic that supports story generation is segregated from an authoring service that executes authoring logic for story generation through an interface. Accordingly, when the authoring service needs analysis from the analysis service, it can invoke the analysis service through the interface. By exposing the analysis service to the authoring service through the shared interface, the details of the logic underlying the analysis service are shielded from the authoring service (and vice versa where the details of the authoring service are shielded from the analysis service). Through parameterization of operating variables, the analysis service can thus be designed as a generalized data analysis service that can operate in a number of different content verticals with respect to a variety of different story types.

Applied artificial intelligence technology for narrative generation using an invocable analysis service

Natural language generation technology is disclosed that applies artificial intelligence to structured data to determine content for expression in natural language narratives that describe the structured data. A graph data structure is employed, where the graph data structure comprises a plurality of nodes. Each of a plurality of the nodes (1) represents a corresponding intent so that a plurality of different nodes represent different corresponding intents and (2) is associated with one or more links to one or more of the nodes to define relationships among the intents. A processor (1) traverses the graph data structure to determine which of the nodes to use for content to be expressed in the natural language narratives and (2) determines which of the nodes to use for providing follow-up information about the natural language narratives based on the links of the graph data structure so that the follow-up information is derived from nodes that are linked to the nodes used for the content to be expressed in the natural language narrative.

Applied artificial intelligence technology for natural language generation using a graph data structure with follow-up capabilities

NLP techniques are disclosed that apply computer technology to sentence data for performing entity referencing. For example, a processor can parse sentence data in a defined window of sentence data into a list of entity terms and a plurality of classifications associated with the listed entity terms. A processor can also a plurality of context saliency scores for a plurality of the listed entity terms based on the classifications associated with the listed entity terms as well as maintain a list of referring terms corresponding to the listed entity terms. For new sentence data that includes a referring term from the referring term list, a processor can (i) select a corresponding entity term on the entity term list based on the context saliency scores for the entity terms, and (ii) infer that the referring term in the new sentence data refers to the selected corresponding entity term.

Context saliency-based deictic parser for natural language processing

NLG techniques are disclosed that apply computer technology to sentence data for performing entity referencing. For example, a processor can parse sentence data in a defined window of sentence data into a list of entity terms and a plurality of classifications associated with the listed entity terms. A processor can also compute a plurality of context saliency scores for a plurality of the listed entity terms based on the classifications associated with the listed entity terms. For new sentence data that refers to an entity term from the entity term list, a processor can select a referring term for referencing that entity term from a list of candidate referring terms based on the context saliency scores for the entity terms. A processor can then form the new sentence data such that the new sentence data includes the selected referring term to refer to the at least one entity term.

Context saliency-based deictic parser for natural language generation

Context Saliency-Based Deictic Parser for Natural Language Processing NLP techniques are disclosed that apply computer technology to sentence data for performing entity referencing. For example, a processor can parse sentence data in a defined window of sentence data into a list of entity terms and a plurality of classifications associated with the listed entity terms. A processor can also a plurality of context saliency scores for a plurality of the listed entity terms based on the classifications associated with the listed entity terms as well as maintain a list of referring terms corresponding to the listed entity terms. For new sentence data that includes a referring term from the referring term list, a processor can (i) select a corresponding entity term on the entity term list based on the context saliency scores for the entity terms, and (ii) infer that the referring term in the new sentence data refers to the selected corresponding entity term.

Disclosed herein are example embodiments of an improved narrative generation system where an analysis service that executes data analysis logic that supports story generation is segregated from an authoring service that executes authoring logic for story generation through an interface. The analysis service may comprise a plurality of analysis applications and a plurality of analysis libraries, where the analysis applications can be segregated from the analysis libraries through another interface. Accordingly, when the authoring service needs analysis from the analysis service, the authoring service can invoke the analysis service through the interface; and when an analysis application needs analysis from an analysis library, the analysis application can invoke the analysis library through the another interface. By exposing the analysis service to the authoring service through the shared interface and by exposing the analysis libraries to the analysis applications through the shared another interface, the details of the logic underlying the analysis service and analysis libraries are shielded from the authoring service and analysis applications respectively (and vice versa).

Applied artificial intelligence technology for narrative generation using an invocable analysis service with analysis libraries

Disclosed herein are example embodiments of an improved narrative generation system where an analysis service that executes data analysis logic, including data re-organization logic, that supports story generation is segregated from an authoring service that executes authoring logic for story generation through an interface. Accordingly, when the authoring service needs analysis from the analysis service, it can invoke the analysis service through the interface. By exposing the analysis service to the authoring service through the shared interface, the details of the logic underlying the analysis service are shielded from the authoring service (and vice versa where the details of the authoring service are shielded from the analysis service). Through parameterization of operating variables, the analysis service can thus be designed as a generalized data analysis service that can operate in a number of different content verticals with respect to a variety of different story types.

Applied artificial intelligence technology for narrative generation using an invocable analysis service and data re-organization

Disclosed herein are example embodiments of an improved narrative generation system where an analysis service that executes data analysis logic that supports story generation can include configuration-driven analytics, such as at least one of a configuration-driven peaks analytic, a configuration-driven jumps analytic, a configuration-driven runs analytic, and/or a configuration-driven streaks analytic. In an example embodiment, the analysis service can be segregated from an authoring service that executes authoring logic for story generation through an interface. Accordingly, when the authoring service needs analysis from the analysis service, it can invoke the analysis service through the interface. By exposing the analysis service to the authoring service through the shared interface, the details of the logic underlying the analysis service are shielded from the authoring service (and vice versa where the details of the authoring service are shielded from the analysis service). Through parameterization of operating variables, the analysis service can thus be designed as a generalized data analysis service that can operate in a number of different content verticals with respect to a variety of different story types.

Growing community of inventors

Chicago, IL, United States of America

Nathan William Krapf