Abstract: A non-transitory computer-readable medium stores instructions readable and executable by at least one electronic processor (20) to perform an augmented reality (AR) content generation method (100). The method includes: acquiring, with a camera (14) of an AR device (13), one or more images of a component of a medical imaging or medical therapy device (12); receiving, from a microphone (15) of the AR device, a triggering audio segment; generating one or more query data structures from both the one or more images and the triggering audio segment; retrieving AR instructional content related to the medical imaging or medical therapy device matching the generated one or more query data structures from a database (26); and outputting the AR instructional content one or more of (i) displayed superimposed on video displayed by the AR device and/or (ii) displayed on a head mounted display of the AR device and/or (iii) as audio content via a loudspeaker (27) of the AR device.

Abstract: Methods and systems for generating text from a haptic-based input. The system may include an interface for receiving a haptic-based input and a processor executing instructions stored on a memory and providing a model. The model is configured to at least receive the haptic-based input and supply a text describing the haptic-based input using the interface.

Abstract: Techniques described herein relate to visual question answering (“VQA”) using trained machine learning models.

Abstract: A method (100) for generating a textual description of a medical image, comprising: receiving (130) a medical image of an anatomical region, the image comprising one or more abnormalities; segmenting (140) the anatomical region in the received medical image from a remainder of the image; identifying (150) at least one of the one or more abnormalities in the segmented anatomical region; extracting (160) one or more features from the identified abnormality; generating (170), using the extracted features and a trained text generation model, a textual description of the identified abnormality; and reporting (180), via a user interface of the system, the generated textual description of the identified abnormality.

Abstract: A method of generating embeddings for a machine learning model, including: extracting a character embedding and a word embedding from a first textual data; generating a domain knowledge embedding from a domain knowledge dataset; combining the character embedding, the word embedding, and the domain knowledge embedding into a combined embedding; and providing the combined embedding to a layer of the machine learning model.

Abstract: The present disclosure pertains to a paraphrase generation system. The system comprises one or more hardware processors and/or other components. The system is configured to obtain a training corpus. The training corpus comprises language and known paraphrases of the language. The system is configured to generate, based on the training corpus, a word-level attention-based model and a character-level attention-based model. The system is configured to provide one or more candidate paraphrases of a natural language input based on both the word-level and character-level attention-based models. The word-level attention-based model is a word-level bidirectional long short term memory (LSTM) network and the character-level attention-based model is a character-level bidirectional LSTM network. The word-level and character level LSTM networks are generated based on words and characters in the training corpus.

Abstract: A method for generating a textual description from a medical image, comprising: receiving a medical image having a first modality to a system configured to generate a textual description of the medical image; determining, using an imaging modality classification module, that the first modality is a specific one of a plurality of different modalities; determining, using an anatomy classification module, that the medical image comprises information about a specific portion of an anatomy; identifying, by an orchestrator module based at least on the determined first modality, which of a plurality of different text generation models to utilize to generate a textual description from the medical image; generating, by a text generation module utilizing the identified text generation model, a textual description from the medical image; and reporting, via a user interface of the system, the generated textual description.

Abstract: Techniques are described herein for training machine learning models to simplify (e.g., paraphrase) complex textual content by ensuring that the machine learning models jointly learn both semantic alignment and notions of simplicity. In various embodiments, an input textual segment having multiple tokens and being associated with a first measure of simplicity may be applied as input across a trained machine learning model to generate an output textual segment. The output textual segment may be is semantically aligned with the input textual segment and associated with a second measure of simplicity that is greater than the first measure of simplicity (e.g., a paraphrase thereof). The trained machine learning model may include an encoder portion and a decoder portion, as well as control layer(s) trained to maximize the second measure of simplicity by replacing token(s) of the input textual segment with replacement token(s).

Abstract: Techniques disclosed herein relate to generating and applying a granular attention hierarchical neural network model to classify a document. In various embodiments, data indicative of the document may be obtained (102) and processed (104) into a first layer of two or more layers of a hierarchical network model using a dual granularity attention mechanism to generate first layer output data, wherein the dual granularity attention mechanism weighs some portions of the data indicative of the document more heavily. Some portions of the data indicative of the document are integrated into the hieratical network model during training of the dual granularity attention mechanism. The first layer output data may be processed (106) in the second of two or more layers of the hierarchical network model to generate second layer output data. A classification label can be generated (108) from the second layer output data.

Abstract: A method for presenting do-it-yourself (DIY) videos to a user related to a user task by a DIY video system, including: receiving a user query including a first image file and a text question from a user regarding the current state of the user task; extracting entities from the first image file to create entity data; extracting question information from the text question; extracting from a DIY video index a video segment related to the user task based upon the entity data and the question information; and presenting the extracted video segment to the user.

Abstract: A method for determining the answer to a query in a document, including: encoding, by an encoder, the query and the document; generating a query-aware context encodings G by a bidirectional attention system using the encoded query and the encoded document; performing a hierarchical self-attention on the query aware document by a hierarchical self-attention system by applying a word to word attention and a word to sentence attention mechanism resulting in a matrix M; and determining the starting word and the ending word of the answer in the document by a span detector based upon the matrix M.

Abstract: A record collection device (201, 400) configured to collect records for an individual (452). The device includes: a user interface (440) configured to receive input from the user, a location module (410) configured to detect a location the device; and a processor (420) configured to: (i) automatically determine, by a processor of the record collection device, that the detected location corresponds to a location where a record may be generated or stored; (ii) receive, from the individual via the user interface, approval to request the record from the determined location; and (iii) send, in response to the individual's input, a request to the determined location for the individual's record.

Abstract: Techniques disclosed herein related to independent and dependent reading using recurrent networks for natural language inference. In various embodiments, data indicative of a premise (310) and data indicative of a hypothesis (312) form a natural language inference classification pair. For example, the data indicative of a premise can be processed independently using a third recurrent network (318) and data indicative of a hypothesis can be processed independently using a first recurrent network (314). Similarly, data indicative of a premise can be processed dependently using a second recurrent network (316) including data indicative of a hypothesis processed independently. Additionally, data indicative of a hypothesis can be processed dependently using a fourth recurrent network (320) including data indicative of a premise processed independently. Independent and dependent premise data can be pooled (334) together. Independent and dependent hypothesis data can be pooled (336) together.

Abstract: Methods and systems for generating a question from free text. The system is trained on a corpus of data and receives a tuple consisting of a paragraph (free text), a focused fact, and a question type. The system implements a language model to find the most optimal combination of words to return a question for the paragraph about the focused fact.

Abstract: A method for determining, from a document, an answer to a query using a query answering system, comprising: (i) encoding, using an encoder, one or more documents; (ii) encoding a received query; (iii) generating, using an attention mechanism, a query-aware document representation comprising alignment between one or more words in one of the plurality of documents and one or more words in the query; (iv) generating, using a hierarchical self-attention mechanism, a word-to-sentence alignment of the query-aware document representation; (v) labeling, using a conditional random field classifier, each of a plurality of words in the word-to-sentence alignment with one of a one of a plurality of different sequence identifiers, resulting in possible labeled answering spans; and (vi) generating, from the one or more possible labeled answering spans, a response to the query.

Abstract: A device, system, and method classifies a cognitive bias in a microblog relative to healthcare-centric evidence. The method performed at a microblog server includes receiving a selection from a clinician, the selection indicating a health-related topic. The method includes determining evidence data of the health-related topic from validated information sources. The method includes receiving a microblog, the microblog associated with the health-related topic. The method includes determining a cognitive bias of the microblog based on the evidence data.

Abstract: Methods and systems for interacting with a user. Systems in accordance with various embodiments described herein provide a collection of models that are each trained to perform a specific function. These models may be categorized into static models that are trained on an existing corpus of information and dynamic models that are trained based on real-time interactions with users. Collectively, the models provide appropriate communications for a user.

Abstract: A system (1000) for automated question answering, including: semantic space (210) generated from a corpus of questions and answers; a user interface (1030) configured to receive a question; and a processor (1100) comprising: (i) a question decomposition engine (1050) configured to decompose the question into a domain, a keyword, and a focus word; (ii) a question similarity generator (1060) configured to identify one or more questions in a semantic space using the decomposed question; (iii) an answer extraction and ranking engine (1080) configured to: extract, from the semantic space, answers associated with the one or more identified questions; and identify one or more of the extracted answers as a best answer; and (iv) an answer tuning engine (1090) configured to fine-tune the identified best answer using one or more of the domain, keyword, and focus word; wherein the fine-tuned answer is provided to the user via the user interface.

Abstract: A method of producing an unsupervised constrained text simplification autoencoder including an encoder and a constrained decoder, including: encoding, by the encoder, input text to produce a code; combining a complexity parameter with the code; decoding, by constrained decoder, the combined code to produce a plurality of outputs, wherein the constrained decoder uses a dropout function to randomize the parameters of the constrained decoder; evaluating a loss function for each of the plurality of outputs, wherein the loss function is based upon the complexity parameter, indicates an achieved text simplification level, and produces an output indicating the difference between the achieved text simplification level and a desired text simplification level; and optimizing the constrained text simplification autoencoder by repeatedly evaluating the loss function for each input text in an input text training data set while varying parameters of the encoder, the parameters of the constrained decoder, and the complexity

Abstract: Various embodiments described herein relate to a method, system, and non-transitory machine-readable medium including one or more of the following: extracting a first concept from input data presented for processing by a downstream function; identifying external data from an external resource based on the first concept; extracting a second concept from the external data; revising the first concept based on the second concept to produce a revised concept, wherein revising includes: applying a machine learning agent to determine whether to keep the first concept or adopt the second concept, and adopting the second concept in place of the first concept for use as the revised concept based on a decision by the machine learning agent to adopt the second concept; and further processing the revised concept according to the downstream function to generate an output.