A general-purpose apparatus for analyzing natural language text that allows for the implementation of a broad range of natural language understanding applications. The apparatus for natural language understanding analyzes a source text and transforms the source text into a semantically-interpretable syntactic representation (SISR), comprising a syntax template and semantic clause annotations. The general-purpose apparatus for natural language understanding is adaptable to various source text natural languages and is adaptable to various natural language understanding applications, such as query answering, translation, summarization, information extraction, disambiguation, and parsing. A natural language query answering apparatus for answering questions about a source text, whereby the query answering apparatus utilizes the general-purpose apparatus for transforming the natural language query into SISR format.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for translating terms using numeric representations. One of the methods includes obtaining data that associates each term in a vocabulary of terms in a first language with a respective high-dimensional representation of the term; obtaining data that associates each term in a vocabulary of terms in a second language with a respective high-dimensional representation of the term; receiving a first language term; and determining a translation into the second language of the first language term from the high-dimensional representation of the first language term and the high-dimensional representations of terms in the vocabulary of terms in the second language.

Techniques for limiting natural language processing performed on input data are described. A system receives input data from a device. The input data corresponds to a command to be executed by the system. The system determines applications likely configured to execute the command. The system performs named entity recognition and intent classification with respect to only the applications likely configured to execute the command.

Various embodiments relating to collecting and auditing structured data layered on unstructured object are disclosed. In one embodiment, a field-data tracking form may include a plurality of input fields layered over an unstructured base object (e.g., a legacy form, document, image, diagram, etc.). Each input field may correspond to a different data object having attributes that maintain a full traceable history of changes made to the input field. The field-data tracking form may act as a data-entry vehicle that can be sent to mobile computers to allow field data to be entered directly into input fields corresponding to the data objects, while maintaining the visual layout of the unstructured base object. Furthermore, attributes of discrete data objects from different versions of the field-data tracking form may be searched and displayed via an audit viewing tool graphical user interface (GUI).

A system for grouping image annotations is disclosed. A display unit (1) is arranged for displaying a plurality of medical images relating to a subject (5) comprising a representation of an anatomical object. An annotation unit (2) is arranged for receiving information regarding input of a plurality of annotations (3) of the plurality of medical images via a user interface (4), wherein each annotation comprises geometric information relative to an image of the plurality of medical images. A grouping unit (4) is arranged for detecting a group of annotations among the plurality of annotations, based on the geometric information and a set of rules that define general properties of geometric relationships of annotations (3) that belong to the same object. The detecting of the group of annotations is further based on a geometric relationship between the plurality of medical images.

Provided is an information processing apparatus including a first reception unit that receives modification to a translation result of at least one first document from a user, a generation unit that generates a translation rule corresponding to the modification received by the first reception unit, a second reception unit that receives original texts of at least one second document, and a utilization unit that utilizes the translation rule generated by the generation unit at the time of translating the original texts received by the second reception unit, depending on relevance between the at least one first document and the second document.

A method to correct for temporal variability in incoming streams of media and data to optimize the performance of a pattern recognition system includes the steps of receiving from one of the incoming streams a point in time when an event is announced, applying probability distribution about the point in time, shifting a point of highest probability of the probability distribution back in time by an amount effective to accommodate for a delay between the event and the announcement, comparing a detected pattern of the event to a stored pattern of similar events and applying a confidence value to the comparison, and confirming to the pattern recognition system that the event occurred at the point of highest probability when the confidence score exceeds a predefined threshold. The method is useful to determine the time at which a particular play occurs during a sporting event, such as the time of a shot-on-goal in a soccer match.

Techniques for generating and providing a checklist, and for providing updates to a checklist based on event data. In some aspects, a checklist is provided to a terminal device by receiving a notification of a trigger event, which is used, at least in part, to obtain a checklist template and to generate a checklist from the checklist template, which is then provided to the terminal device. In some aspects, a server device provides a checklist to a terminal device, the checklist comprising a sequence of prompts, each prompt indicating one or more actions, and the server device provides an update to the checklist based on received event data.

A method and computer readable medium for defining pagination preferences that control pagination of dynamic-length presentations. In an embodiment, a computer implemented method for specifying pagination preferences comprises, identifying pagination preferences for each page of an original presentation, recording the starting point and ending point within the primary text flow that appear on each page, associating the elements with the page on which the elements are located and storing the pagination preferences, starting and ending points in the primary text flow, and page elements as metadata associated with each page.

The present invention provides recommendation of top scoring form fragments to a form designer. A plurality of form fragments may be stored in a form repository, each form fragment including user-defined form fragment attributes, and analytics data for the form fragments may be collected over a period of time to calculate a performance score for each of the form fragments. When an author searches for a form fragment, at least one matching form fragment from the form repository may be obtained based on the search query or criteria inputted by the author using natural language processing (NLP). The matching form fragments may be ordered based on the performance score, where higher performing form fragments are listed first. The ordered form fragments may be displayed on a device associated with the author so that the form fragments may be used by the author when authoring forms.