Abstract: Systems and processes for word prediction using multiple contexts are provided. For example, a plurality of words are received. A first word context including a first plurality of received words, and a second word context corresponding to the first plurality of received words and a second plurality of received words, are obtained. A first current word probability is determined based on a first language model using the first word context. A second current word probability is determined based on a second language model using the second word context. A third current word probability is determined based on the second language model using the first word context. A fourth current word probability is determined based on the first current word probability, the second current word probability, and the third current word probability. An output is provided, to a user, including a current word prediction based on the fourth current word probability.

Abstract: Systems and methods are disclosed for automatically scoring a constructed response using a neural network. In embodiments, a constructed response received by a processing system may be processed to divide the constructed response into multiple series of word tokens, wherein each word token includes a sequence of characters. The constructed response may be further processed to correct one or more spelling errors. The word tokens may be encoded to generate representation vectors for the constructed response. A set of nonlinear operations may be applied to the plurality of representation vectors in a neural network to generate a single vector output. A set of predetermined network weights may be applied to the vector output of the neural network to generate a scalar output for scoring the constructed response.

Abstract: A system comprises a server including a port, memory and processing circuitry. The port is configured to receive (i) a drawing file associated with an isometric drawing of an asset at an inspection site including indications of condition monitoring locations (CMLs) for the asset, and (ii) inspection measurement data for the asset, the inspection measurement data including inspection measurements associated with the CMLs. The memory is configured to store the drawing file and the inspection measurement data. The processing circuitry is configured to use the inspection data and the drawing file to generate, using the inspection measurement data and the drawing file, (i) survey image data for display and (ii) metadata for the survey image data, the metadata including survey image coordinates for the CMLs and the inspection measurements associated with the CMLs.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the methods includes the steps of receiving a first set of labeled data from a first data source; receiving a text string from a second data source; performing natural language processing on the text string to extract particular text portions and generate a second set of labeled data; performing a comparison between the first set of labeled data and the second set of labeled data; and generating an output based on the comparison.

Abstract: Described are medias, systems, and computer-implemented methods to detect improper residency status by performing a data mining task to data source to detect one or more improper residency indicia, applying a machine learning algorithm to identify an initial candidate, calculating a probability that the initial candidate has an improper residency status, and validating the detection. Further described are medias, systems, and computer-implemented methods to detect improper occupancy tax status. Further described are medias, systems, and computer-implemented methods to detect an improper homeowner exemption.

Abstract: Systems and techniques for linguistically-driven automated text formatting are described herein. Data representing the linguistic structure of input text may be received from Natural Language Processing (NLP) Services, including but not limited to constituents, dependencies, and coreference relationships. A text model of the input text may be built using the linguistic components and relationships. Cascade rules may be applied to the text model to generate a cascaded text data structure. Cascaded data may be displayed on a range of media, including a phone, tablet, laptop, monitor, VR/AR devices. Cascaded data may be presented in dual screen formats to promote more accurate and efficient reading comprehension, greater ease in teaching native and foreign language grammatical structures, and tools for remediation of reading-related disabilities.

Abstract: Techniques are described related to prior context retrieval with an automated assistant. In various implementations, instance(s) of free-form natural language input received from a user during a human-to-computer dialog session between the user and an automated assistant may be used to generate a first dialog context. The first dialog context may include intent(s) and slot value(s) associated with the intent(s). Similar operations may be performed with additional inputs to generate a second dialog context that is semantically distinct from the first dialog context. When a command is received from the user to transition the automated assistant back to the first dialog context, natural language output may be generated that conveys at least one or more of the intents of the first dialog context and one or more of the slot values of the first dialog context. This natural language output may be presented to the user.

Abstract: A method of electronic communication assistance is provided. The method includes receiving, via an artificial intelligence assistant computing facility, an electronic communication from a first user intended to be received by a second user; and determining, via the artificial intelligence assistant computing facility, a capacity of the second user to receive the electronic communication. The method further includes determining, via the artificial intelligence assistant computing facility and based at least in part on the capacity of the second user, a time to send the electronic communication; and transmitting, via the artificial intelligence assistant computing facility, the time to the first user.

Abstract: Methods, systems, and computing devices for visualizing natural language processing algorithm processes are described herein. A plurality of categories may be determined. Each color of a plurality of colors may correspond to the categories. Text content may be processed using a natural language processing algorithm. Confidence values indicating, for each of a plurality of portions of the text content, a degree of confidence corresponding to one or more of the plurality of categories may be determined. Display colors may be determined based on the confidence values. A user interface comprising a visualization of the text content may be displayed, and the user interface may be configured to show each portion of the text content using a display color such that the user interface indicates changes in confidence across the plurality of characters.

Abstract: A system for generating product label changes is described. The system includes a product labeling platform executable on a network enabled computing device and a database of at least one selectable master label and at least one selectable jurisdiction label associated with a labeled product. The platform associates at least one selected descriptor from a first pre-defined descriptor set to each change made to a selected master label, and further associates at least one selected descriptor from a second pre-defined descriptor set to each change made to a selected jurisdiction label. The platform further associates a report including the selected descriptors from the first and second pre-defined descriptor sets with the changed label. A system for generating and managing product labels for a product across multiple jurisdictions is also disclosed.

Abstract: An online system extracts information from non-fixed form documents. The online system receives an image of a form document and obtains a set of phrases and locations of the set of phrases on the form image. For at least one field, the online system determines key scores for the set of phrases. The online system identifies a set of candidate values for the field from the set of identified phrases and identifies a set of neighbors for each candidate value from the set of identified phrases. The online system determines neighbor scores, where a neighbor score for a candidate value and a respective neighbor is determined based on the key score for the neighbor and a spatial relationship of the neighbor to the candidate value. The online system selects a candidate value and a respective neighbor based on the neighbor score as the value and key for the field.

Abstract: The present disclosure relates to chatbot systems and, more particularly, to techniques for determining that an input utterance is representative of a task that a particular chatbot can perform, based on matching the input utterance to a template. Techniques are also described for generating templates based on example utterances that have been provided for a chatbot. In certain embodiments, an initial set of templates is generated based on example utterances. This initial set of templates is then refined using template generalization techniques, which can be performed at the word or sentence level to generate a final set of templates for use at runtime, when the templates are matched against user utterances. The final set of templates may include one or more generalized templates that were derived from the initial set of templates and may also include the initial set of templates.

Abstract: Methods and systems are presented for automatically scrubbing sensitive data from text data comprising a sequence of words based on a negative word index. The negative word index may be constructed by obtaining articles that are publicly available and extracting words and word sequences from the articles. Statistical information associated with the word and word sequences from the articles may also be determined and included in the negative word index. To scrub sensitive data from the text data, a first sub-sequence of words is identified from the text data. The first sub-sequence of words may be determined to include sensitive information or not based on statistical information associated with the first sub-sequence of words within the negative word index. If the first sub-sequence of words includes sensitive information, the first sub-sequence of words may be removed from the text data.

Abstract: Systems and methods as disclosed herein are provided for generating a research study application. A request to generate a research study is received from a user. A plurality of task generation options are presented on a graphical user interface of an electronic device. The plurality of task generation options are selected from the group consisting of a consent survey, an eligibility survey, a medical history survey, and a medical tracking survey. Input regarding the plurality of task generation options is received from the user. Additionally, a research study application is generated based on information received from the user.

Abstract: In some embodiments, a method includes identifying a set of word bounding boxes in a first electronic document, and identifying locations of horizontal white space between two adjacent rows from a set of rows in a table. The method includes determining, using a Natural Language Processing algorithm, an entity name from a set of entity names for each table cell from a set of table cells in the table. The method includes determining, using a machine learning algorithm a class from a set of classes for each row from the set of rows. The method includes extracting a set of table cell values associated with the set of table cells, and generating a second electronic document including the set of table cell values arranged in the set of rows and the set of columns such that the set of words in the table are computer-readable in the second electronic document.

Abstract: This disclosure relates generally to methods and systems for automatic extraction of self-reported activities of an individual from a freestyle narrative text. Manual extraction of such self-reported activities of the individual from the freestyle narrative text over the period of time is a complex task and consume a significant amount of time. The present systems and methods utilize a predefined grammar pattern and a natural language processing technique to generate one or more candidate activity phrases, from the pre-processed input text posted by the individual. A deep learning based supervised classification model is utilized to automatically extract the one or more self-reported activities of the individual, from the one or more candidate activity phrases. Manual intervention and efforts of analyzing the freestyle narrative text to extract the self-reported activities are avoided. Longitudinal assessment of the self-reported activities may reveal routines and behavior of the individual.

Abstract: Methods for generating content summaries in a web content management service, wherein in one embodiment a digital page editor and a component browser are launched to enable selection of a first content item. A summary of the first content item is automatically generated according to parameters that may have default values or values set by a user. The parameters may specify a size for the summary as a percentage of the first content item's size, as a particular number of lines, characters or words, as a size for a particular type of device, etc. The automatically generated summary is provided to the digital page editor, which can edit it and add it to the digital page. The summary is stored in a content repository as an independent summary content item with its own metadata.

Abstract: An NLP analysis method based on identification of common terms is disclosed. The improved NLP analysis can separate different parts of a patent claim into discrete claim segments based on the common terms. A user interface that corresponds to a flowchart allows the user to drag and drop the claim segments to form complex relationships, which is used to generate a patent specification.

Abstract: A method of identifying text (e.g., a sentence or sentence portion) in a word processing text editor; automatically identifying a domain-specific deep-learning neural network that corresponds to an identified context, from among one or more domain-specific deep-learning neural networks; automatically identifying at least one suggested replacement word using the identified domain specific deep-learning neural network that corresponds to the identified context; and automatically controlling a display to display a user interface that includes functionality that presents prompt information that includes the at least one suggested replacement word. Changes for errors that are common in academic papers written by non-native speakers may be suggested.

Abstract: Disclosed herein is attack-less adversarial training for robust adversarial defense. The attack-less adversarial training for robust adversarial defense includes the steps of: (a) generating individual intervals (ci) by setting the range of color (C) and then discretizing the range of color (C) by a predetermined number (k); (b) generating one batch from an original image (X) and training a learning model with the batch; (c) predicting individual interval indices (?ialat) from respective pixels (xi) of the original image (X) by using an activation function; (d) generating a new image (Xalat) through mapping and randomization; and (e) training a convolutional neural network with the image (Xalat) generated in step (d) and outputting a predicted label (?).