Abstract: A method and system for generating training data for training a gesture detection machine-learning (ML) model includes receiving a request to generate training data for the gesture detection model, the training data being associated with a target gesture, retrieving data associated with an original gesture, the original gesture being a gesture made using a body part, retrieving skeleton data associated with the target gesture, the skeleton data displaying a skeleton representative of the body part and the skeleton displaying the target gesture, aligning a location of the body part in the data with a location of the skeleton in the skeleton data, providing the aligned data and the skeleton data to an ML model for generating a target data that displays the target gesture, receiving the target data as an output from the ML model, the target data preserving a visual feature of the data and displaying the target gesture, and providing the target data to the gesture detection ML model.

Abstract: Aspects of the present disclosure relate to systems and methods for detecting and correcting undesirable content. A video feed may be segmented to distinguish background data from foreground data. It may be determined that a region of the background data includes a qualifying behavior. The qualifying behavior may be classified as belonging to a distracting category of data. An effect may be applied to the background data that includes the qualifying behavior to reduce an appearance of the qualifying behavior.

Abstract: The present disclosure relates to processing operations that execute image classification training for domain-specific traffic, where training operations are entirely compliant with data privacy regulations and policies. Image classification model training, as described herein, is configured to classify meaningful image categories in domain-specific scenarios where there is unknown data traffic and strict data compliance requirements that result in privacy-limited image data sets. Iterative image classification training satisfies data compliance requirements through a combination of online image classification training and offline image classification training. This results in tuned image recognition classifiers that have improved accuracy and efficiency over general image recognition classifiers when working with domain-specific data traffic. One or more image recognition classifiers are independently trained and tuned to detect an image class for image classification.

Abstract: Automatic generation of intelligent content is created using a system of computers including a user device and a cloud-based component that processes the user information. The system performs a process that includes receiving an input document and parsing the input document to generate inputs for a natural language generation model using a text analysis model. The natural language generation model generates one or more candidate presentation scripts based on the inputs. A presentation script is selected from the candidate presentation scripts and displayed. A text-to-speech model may be used to generate a synthesized audio presentation of the presentation script. A final presentation may be generated that includes a visual display of the input document and the corresponding audio presentation in sync with the visual display.

Abstract: Automatic generation of intelligent content is created using a system of computers including a user device and a cloud-based component that processes the user information. The system performs a process that includes receiving a user query for creating content in a content generation application and determining an action from an intent of the user query. A prompt is generated based on the action and provided to a natural language generation model. In response to the prompt, output is received from the natural language generation model. Response content is generated based on the output in a format compatible with the content generation application. At least some of the response content is displayed to the user. The user can choose to keep, edit, or discard the response content. The user can iterate with additional queries until the content document reflects the user's desired content.

Abstract: A method and system for detecting one or more speech features in speech audio data includes receiving speech audio data, performing preprocessing on the speech audio data to prepare the speech audio data for use as an input into one or more models that detect one or more speech features, providing the preprocessed speech audio data to a stacked machine learning model, and analyzing the preprocessed speech audio data via the stacked ML model to detect the one or more speech features. The stacked ML model includes a feature aggregation model, a sequence to sequence model, and a decision-making model.

Abstract: A method and system for providing an application-specific embedding for an entire text-to-content suggestions service is disclosed. The method includes accessing a dataset containing unlabeled training data collected from an application, the unlabeled training data being collected under user privacy constraints, applying an unsupervised ML model to the dataset to generate a pretrained embedding; and utilizing the pretrained embedding to train the text-to-content suggestion ML model utilized by the application.

Abstract: Method and system for training a text-to-content suggestion ML model include accessing a dataset containing unlabeled training data collected from an application, the unlabeled training data being collected under user privacy constraints, applying an ML model to the dataset to generate a pretrained embedding, and applying a supervised ML model to a labeled dataset to train the text-to-content suggestion ML model utilized by the application by utilizing the pretrained embedding generated by the supervised ML model.

Abstract: Disclosed herein is a process of making a compound of formula I The compound of formula I is an inhibitor of MEK and thus can be used to treat cancer.

Abstract: Automatic generation of intelligent content is created using a system of computers including a user device and a cloud-based component that processes the user information. The system performs a process that includes receiving a user query for creating content in a content generation application and determining an action from an intent of the user query. A prompt is generated based on the action and provided to a natural language generation model. In response to the prompt, output is received from the natural language generation model. Response content is generated based on the output in a format compatible with the content generation application. At least some of the response content is displayed to the user. The user can choose to keep, edit, or discard the response content. The user can iterate with additional queries until the content document reflects the user's desired content.

Abstract: A data processing system for generating training data for a multilingual NLP model implements obtaining a corpus including first and second content items, where the first content items are English-language textual content, and the second content items are translations of the first content items in one or more non-English target languages; selecting a first content item from the plurality of first content items; generating a plurality of candidate labels for the first content item by analyzing the first content item with a plurality of first English-language NLP models; selecting a first label from the plurality of candidate labels; generating first training data by associating the first label with the first content item; generating second training data by associating the first label with a second content item of the second content items; and training a pretrained multilingual NLP model with the first training data and the second training data.

Abstract: An intelligent speech assistant receives information collected while a user is speaking. The information can comprise speech data, vision data, or both, where the speech data is from the user speaking and the vision data is of the user while speaking. The assistant evaluates the speech data against a script which can contain information that the user should speak, information that the user should not speak, or both. The assistant collects instances where the user utters phrases that match the script or instances where the user utters phrases that do not match the script, depending on whether phases should or should not be spoken. The assistant evaluates vision data to identify gestures, facial expressions, and/or emotions of the user. Instances where the gestures, facial expressions, and/or emotions are not appropriate to the context are flagged. Real-time prompts and/or a summary is presented to the user as feedback.

Abstract: The present disclosure applies trained artificial intelligence (AI) processing adapted to automatically generating transformations of formatted templates. Pre-existing formatted templates (e.g., slide-based presentation templates) are leveraged by the trained AI processing to automatically generate a plurality of high-quality template transformations. In transforming a formatted template, the trained AI processing not only generates feature transformation of objects thereof but may also provide style transformations where attributes associated with a presentation theme may be modified for a formatted template or set of formatted templates. The trained AI processing is novel in that it is tailored for analysis of feature data of a specific type of formatted template.

Abstract: Techniques performed by a data processing system for facilitating an online presentation session include establishing the session for a first computing device of a presenter and a plurality of second computing devices of a plurality of participants, receiving a set of first media streams comprising presentation content from the first computing device, sending a set of second media streams to the plurality of second computing devices, receiving a set of third media streams from the computing devices of a first subset of the plurality of participants including video content of first subset of the participants captured by the respective computing devices of the first subset of participants, analyzing the set of third media streams to identify a set of first reactions by the first subset participants to obtain first reaction information, determining first graphical representation information representing the first reaction information, and sending a fourth media stream to cause the first computing device to displ

Abstract: Techniques performed by a data processing system for facilitating an online presentation session include establishing an online presentation session for conducting an online presentation for a first computing device of a presenter and a plurality of second computing devices of a plurality of participants, receiving a set of first media streams comprising presentation content from the first computing device, receiving a set of second media streams from the second computing devices of a first subset of the plurality of participants, the set of second media streams including audio content, video content, or both of first subset of the plurality of participants, analyzing the set of first media streams using one or more first machine learning models n to generate a set of first feedback results, analyzing the set of second media streams using one or more second machine learning models to identify a set of first reactions by the participants to obtain first reaction information, automatically analyzing the set of

Abstract: The present disclosure provides polysorbate 20 compositions with particular fatty acid ester concentrations. In some embodiments, they may be used in pharmaceutical formulations, for example, to improve stability.

Abstract: Examples are disclosed that relate to methods and computing devices for providing voice-based assistance during a presentation. In one example, a method comprises receiving content of a slide deck, processing the content of the slide deck, and populating a contextual knowledge graph based on the content of the slide deck. A voice input is received from a presenter. Using the knowledge graph, the voice input is analyzed to determine an action to be performed by a presentation program during the presentation. The action is translated into one or more commands executable by the presentation program to perform the action, and the one or more commands are sent to a client device executing the presentation program.

Abstract: A textual user input is received and a plurality of different text-to-content models are run on the textual user input. A selection system attempts to identify a suggested content item, based upon the outputs of the text-to-content models. The selection system first attempts to generate a completed suggestion based on outputs from a single text-to-content model. It then attempts to mix the outputs of the text-to-content models to obtain a completed content suggestion.

Abstract: The present disclosure relates to processing operations configured to provide processing that automatically analyzes acoustic signals from attendees of a live presentation and automatically triggers corresponding reaction indications from results of analysis thereof. Exemplary reaction indications provide feedback for live presentations that can be presented in real-time (or near real-time) without requiring a user to manually take action to provide any feedback. As a non-limiting example, reaction indications may be presented in a form that is easy to visualize and understand such as emojis or icons. Another example of a reaction indication is a graphical user interface (GUI) notification that provides a predictive indication of user intent derived from analysis of acoustic signals.

Abstract: Methods, systems, and computer programs are presented for detecting a mission changes in a conversation. A user utterance from a user device is received. The user utterance is part of a conversation with an intelligent assistant. The conversation includes preceding user utterances in pursuit of a first mission. It is determined that the user utterance indicates a mission change from the first mission to a second mission based on an application of a machine-learned model to the user utterance and the preceding user utterances. The machine-learned model has been trained repeatedly with past utterances of other users over a time period, the determining based on a certainty of the indication satisfying a certainty threshold. Responsive to the determining that the user utterance indicates the mission change from the first mission to a second mission, a reply to the user utterance is generated to further the second mission rather than the first mission.