A method for more efficient structural parsing of binary representations of text based objects within a data distribution system. Clients subscribe to a topic maintained by the data distribution system server that publishers can publish to. Clients receive an original binary representation of a text based object describing the state of the topic to which the client is subscribed. In response to the state of the topic changing at the data distribution system server, clients receive a binary delta representing the change of the state of the topic. Based on the received binary representation and the binary delta, clients calculate an updated binary representation of the text based object. Using the original binary representation, the updated binary representation, and the binary delta, the client generates a structural delta representing the structural differences between data structures of the original text based object and data structures of the updated text based object.

Implementations are described herein for automatically annotating or curating digital images using various signals generated by individual users, in addition to or instead of content of the digital images themselves, thereby to enable the digital images to be retrieved from a searchable database based on their annotations. In particular, techniques are described herein for identifying events associated with a user, e.g., based on natural language input provided by a user, and automatically classifying/annotating images inferred to be related to those events.

Implementations are described herein for automatically annotating or curating digital images using various signals generated by individual users, in addition to or instead of content of the digital images themselves, thereby to enable the digital images to be retrieved from a searchable database based on their annotations. In particular, techniques are described herein for identifying events associated with a user, e.g., based on natural language input provided by a user, and automatically classifying/annotating images inferred to be related to those events.

A research assistant system may include a research tool and components and a user interface to discover and evidence answers to complex research questions. The research tools may include components to iteratively perform steps in a research process, including searching, analyzing, connecting, aggregating, synthesizing, and chaining together evidence from a diverse set of knowledge sources. The system may receive an input query and perform a semantic search for key concepts in a text corpus. A semantic parser may interpret the search results. The system may aggregate and synthesize information from interpreted results. The system may rank and score the aggregated results data and present data on the user interface. The user interface may include prompts to iteratively guide user input to explore evidentiary chains and connect research concepts to produce research results annotated by evidence passages.

Systems, methods and computer program code to propose annotations are provided which include identifying an input, applying a grouping model to the input to predict at least a first grouping concept associated with the input, comparing the at least first grouping concept to a set of relationship data to select at least a first ranking model, applying the at least first ranking model to the input to predict at least a first ranking concept associated with the input, and causing a user interface to display the input, the at least first grouping concept and the at least first ranking concept to a user as proposed annotations of the input.

Systems, methods and computer program code to propose annotations are provided which include identifying an input, applying a grouping model to the input to predict at least a first grouping concept associated with the input, comparing the at least first grouping concept to a set of relationship data to select at least a first ranking model, applying the at least first ranking model to the input to predict at least a first ranking concept associated with the input, and causing a user interface to display the input, the at least first grouping concept and the at least first ranking concept to a user as proposed annotations of the input.

A research assistant system may include a research tool and components and a user interface to discover and evidence answers to complex research questions. The research tools may include components to iteratively perform steps in a research process, including searching, analyzing, connecting, aggregating, synthesizing, and chaining together evidence from a diverse set of knowledge sources. The system may receive an input query and perform a semantic search for key concepts in a text corpus. A semantic parser may interpret the search results. The system may aggregate and synthesize information from interpreted results. The system may rank and score the aggregated results data and present data on the user interface. The user interface may include prompts to iteratively guide user input to explore evidentiary chains and connect research concepts to produce research results annotated by evidence passages.

A research assistant system may include a research tool and components and a user interface to discover and evidence answers to complex research questions. The research tools may include components to iteratively perform steps in a research process, including searching, analyzing, connecting, aggregating, synthesizing, and chaining together evidence from a diverse set of knowledge sources. The system may receive an input query and perform a semantic search for key concepts in a text corpus. A semantic parser may interpret the search results. The system may aggregate and synthesize information from interpreted results. The system may rank and score the aggregated results data and present data on the user interface. The user interface may include prompts to iteratively guide user input to explore evidentiary chains and connect research concepts to produce research results annotated by evidence passages.

According to one implementation, a system includes a computing platform having processing hardware, and a system memory storing a software code. The processing hardware is configured to execute the software code to receive a vocabulary, identify words from the vocabulary for use in extending the vocabulary, pair each of those words with every other of those words to provide word pairs, and output the word pairs to a vocabulary administrator. The software code also receives word pair characterizations identifying each of the word pairs as one of similar, dissimilar, or neither similar nor dissimilar, configures, based on the word pair characterizations, a multi-dimensional vector space including multiple embedding vectors each corresponding respectively to one of the identified words, and cross-references each of those words with its corresponding embedding vector to produce an extended vocabulary corresponding to the received vocabulary.

According to one implementation, a system includes a computing platform having processing hardware, and a system memory storing a software code. The processing hardware is configured to execute the software code to receive a vocabulary, identify words from the vocabulary for use in extending the vocabulary, pair each of those words with every other of those words to provide word pairs, and output the word pairs to a vocabulary administrator. The software code also receives word pair characterizations identifying each of the word pairs as one of similar, dissimilar, or neither similar nor dissimilar, configures, based on the word pair characterizations, a multi-dimensional vector space including multiple embedding vectors each corresponding respectively to one of the identified words, and cross-references each of those words with its corresponding embedding vector to produce an extended vocabulary corresponding to the received vocabulary.