Abstract: 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.

Abstract: 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.

Abstract: 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) dynamically determines a size for a natural language narrative and (2) traverses the graph data structure based on the determined size and a plurality of the links to determine which of the nodes to use for content to be expressed in the natural language narrative having the determined size.

Abstract: 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.

Abstract: 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 structurer code based on a plurality of operating rules and/or parameters that control how the structurer code organizes the items of content into a story outline from which the natural language narrative is generated, wherein the operating rules and/or parameters are configurable to change strategies for organizing the items of content into the story outline.

Abstract: 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.

Abstract: 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.

Abstract: 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 different nodes represent different corresponding intents, (2) is associated with a result that represents an evaluation of the node's corresponding intent with respect to the structured data, and (3) is associated with one or more links to 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 choose which of the results are to be expressed in the natural language narratives.

Abstract: 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 code corresponding to any of a plurality of different choosers that traverse the graph data structure to determine which of the nodes to use for content to be expressed in the natural language narratives, wherein the different choosers comprise different operating rules and/or parameters that implement different strategies for choosing which nodes are used for the content to be expressed in the natural language narratives.

Abstract: 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.

Abstract: A deck for a lift device includes a floor that defines a surface, a pair of side portions, multiple wear pads, multiple pins, and a hand rail. The pair of side portions are positioned on opposite sides of the floor. Each of the pair of side portions is configured to define a channel configured to receive a middle rail of a platform of the lift device. At least one wear pad is positioned within each of the channels and abuts a top of the middle rail. The pins are removably inserted into openings of the side portions. The pins are configured to extend past a bottom surface of the middle rail to limit removal of the deck from the middle rail. The hand rail extends from a rear portion of the deck.

Abstract: A computer-implemented method for synthesizing speech audio includes obtaining a grammatical profile defining an input text of actual words as a function of at least syllable-occurrence rates and syllable-count-per-word rates; generating a dictionary of pseudo-words having the syllable-count-per-word rates, each pseudo-word consisting of one syllable or concatenated syllables selected from the input text, wherein substantially all of the pseudo-words are not actual words; constructing an output text product having the grammatical profile, the output text product comprising at least one sentence consisting of one or more pseudo-words selected from the dictionary; and synthesizing speech audio using the output text product. Related systems and computer-readable media are also provided.

Abstract: A computer-implemented method for synthesizing speech audio includes obtaining a grammatical profile defining an input text of actual words as a function of at least syllable-occurrence rates and syllable-count-per-word rates; generating a dictionary of pseudo-words having the syllable-count-per-word rates, each pseudo-word consisting of one syllable or concatenated syllables selected from the input text, wherein substantially all of the pseudo-words are not actual words; constructing an output text product having the grammatical profile, the output text product comprising at least one sentence consisting of one or more pseudo-words selected from the dictionary; and synthesizing speech audio using the output text product. Related systems and computer-readable media are also provided.

Abstract: An automated interface generates a tree of design actions based on a predetermined design specification, each intermediary node of the tree representing a partial user interface design, and each branch of the tree representing a design action that creates or modifies the partial user interface design. A plurality of candidate user interface designs are determined, each implementing the received plurality of functions, by traversing the tree along multiple traversal paths from a root node of the tree to respective leaf nodes of the tree and executing respective design actions represented by branches along the traversal paths. A completed interface design is selected from the plurality of completed interface designs, and the final user interface is generated based on the selected candidate user interface design.

Abstract: Automated processing of web tasks provides information relevant to user tasks based on past user actions and web histories. Automating the processing of tasks includes receiving a task which may be sent from a system such as a short messaging system (SMS), an email system, or a telephone system. Command information is extracted from the task. A sequence of actions is generated to accomplish the task including a combined script. The script may be based on past user actions, logs, and web browsing histories. The sequence of actions is executed to return information relevant to the task.

Abstract: In an aspect of the invention, a method of communication comprises: establishing an asynchronous communication stream between a first user and a second user; and sending clipped dynamic content from the second user to the first user via the asynchronous communication stream, the clipped dynamic content selected and extracted from a web page by the second user.

Abstract: An automated interface generates a tree of design actions based on a predetermined design specification, each intermediary node of the tree representing a partial user interface design, and each branch of the tree representing a design action that creates or modifies the partial user interface design. A plurality of candidate user interface designs are determined, each implementing the received plurality of functions, by traversing the tree along multiple traversal paths from a root node of the tree to respective leaf nodes of the tree and executing respective design actions represented by branches along the traversal paths. A completed interface design is selected from the plurality of completed interface designs, and the final user interface is generated based on the selected candidate user interface design.

Abstract: An automated interface generates a tree of design actions based on a predetermined set of functions and relationship information, each intermediary node of the tree representing a partial user interface design, and each branch of the tree representing a design action that creates or modifies the partial user interface design. A plurality of candidate user interface designs are determined, each implementing the received plurality of functions, by traversing the tree along multiple traversal paths from a root node of the tree to respective leaf nodes of the tree and executing respective design actions represented by branches along the traversal paths. A completed interface design is selected from the plurality of completed interface designs based on a predetermined selection algorithm, and the final user interface is generated based on the selected candidate user interface design.