Abstract: Systems and methods for document editing are provided. One aspect of the systems and methods includes obtaining a document and a natural language edit request. Another aspect of the systems and methods includes generating a structured edit command using a machine learning model based on the document and the natural language edit request. Yet another aspect of the systems and methods includes generating a modified document based on the document and the structured edit command, where the modified document includes a revision of the document that incorporates the natural language edit request.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generate a digital document hierarchy comprising layers of parent-child element relationships from the visual elements. For example, for a layer of the layers, the disclosed systems determine, from the visual elements, candidate parent visual elements and child visual elements. In addition, for the layer of the layers, the disclosed systems generate, from the feature embeddings utilizing a neural network, element classifications for the candidate parent visual elements and parent-child element link probabilities for the candidate parent visual elements and the child visual elements. Moreover, for the layer, the disclosed systems select parent visual elements from the candidate parent visual elements based on the parent-child element link probabilities. Further, the disclosed systems utilize the digital document hierarchy to generate an interactive digital document from the digital document image.

Abstract: In implementations of systems for training language models and preserving privacy, a computing device implements a privacy system to predict a next word after a last word in a sequence of words by processing input data using a machine learning model trained on training data to predict next words after last words in sequences of words. The training data describes a corpus of text associated with clients and including sensitive samples and non-sensitive samples. The machine learning model is trained by sampling a client of the clients and using a subset of the sensitive samples associated with the client and a subset of the non-sensitive samples associated with the client to update parameters of the machine learning model. The privacy system generates an indication of the next word after the last word in the sequence of words for display in a user interface.

Abstract: Systems and methods for document classification are described. Embodiments of the present disclosure generate classification data for a plurality of samples using a neural network trained to identify a plurality of known classes; select a set of samples for annotation from the plurality of samples using an open-set metric based on the classification data, wherein the annotation includes an unknown class; and train the neural network to identify the unknown class based on the annotation of the set of samples.

Abstract: In various examples, a table recognition model receives an image of a table and generates, using a first encoder of the table recognition machine learning model, an image feature vector including features extracted from the image of the table; generates, using a first decoder of the table recognition machine learning model and the image feature vector, a set of coordinates within the image representing rows and columns associated with the table, and generates, using a second decoder of the table recognition machine learning model and the image feature vector, a set of bounding boxes and semantic features associated with cells the table, then determines, using a third decoder of the table recognition machine learning model, a table structure associated with the table using the image feature vector, the set of coordinates, the set of bounding boxes, and the semantic features.

Abstract: One example method involves operations for a processing device that include receiving, by a machine learning model trained to generate a search result, a search query for a text input. The machine learning model is trained by receiving pre-training data that includes multiple documents. Pre-training the machine learning model by generating, using an encoder, feature embeddings for each of the documents included in the pre-training data. The feature embeddings are generated by applying a masking function to visual and textual features in the documents. Training the machine learning model also includes generating, using the feature embeddings, output features for the documents by concatenating the feature embeddings and applying a non-linear mapping to the feature embeddings. Training the machine learning model further includes applying a linear classifier to the output features. Additionally, operations include generating, for display, a search result using the machine learning model based on the input.

Abstract: Systems and methods for image segmentation are described. Embodiments of the present disclosure receive a training image and a caption for the training image, wherein the caption includes text describing an object in the training image; generate a pseudo mask for the object using a teacher network based on the text describing the object; generate a mask for the object using a student network; compute noise information for the training image using a noise estimation network; and update parameters of the student network based on the mask, the pseudo mask, and the noise information.

Abstract: Embodiments are provided for facilitating multimodal extraction across multiple granularities. In one implementation, a set of features of a document for a plurality of granularities of the document is obtained. Via a machine learning model, the set of features of the document are modified to generate a set of modified features using a set of self-attention values to determine relationships within a first type of feature and a set of cross-attention values to determine relationships between the first type of feature and a second type of feature. Thereafter, the set of modified features are provided to a second machine learning model to perform a classification task.

Abstract: Systems and methods for product retrieval are described. One or more aspects of the systems and methods include receiving a query that includes a text description of a product associated with a brand; identifying the product based on the query by comparing the text description to a product embedding of the product, wherein the product embedding is based on a brand embedding of the brand; and displaying product information for the product in response to the query, wherein the product information includes the brand.

Abstract: The technology described herein is directed to an adaptive sparse attention pattern that is learned during fine-tuning and deployed in a machine-learning model. In aspects, a row or a column in an attention matrix with an importance score for a task that is above a threshold importance score is identified. The important row or the column is included in an adaptive attention pattern used with a machine-learning model having a self-attention operation. In response to an input, a task-specific inference is generated for the input using the machine-learning model with the adaptive attention pattern.

Abstract: Systems, methods, and non-transitory computer-readable media can generate a natural language model that provides user-entity differential privacy. For example, in one or more embodiments, a system samples sensitive data points from a natural language dataset. Using the sampled sensitive data points, the system determines gradient values corresponding to the natural language model. Further, the system generates noise for the natural language model. The system generates parameters for the natural language model using the gradient values and the noise, facilitating simultaneous protection of the users and sensitive entities associated with the natural language dataset. In some implementations, the system generates the natural language model through an iterative process (e.g., by iteratively modifying the parameters).

Abstract: Systems and methods for image processing are described. Embodiments of the present disclosure receive a training image and a caption for the training image, wherein the caption includes text describing an object in the training image; generate a pseudo mask for the object using a teacher network based on the text describing the object; generate a mask for the object using a student network; and update parameters of the student network based on the mask and the pseudo mask.

Abstract: Methods and systems are provided for facilitating identification of fillable regions and/or data associated therewith. In embodiments, a candidate fillable region indicating a region in a form that is a candidate for being fillable is obtained. Textual context indicating text from the form and spatial context indicating positions of the text within the form are also obtained. Fillable region data associated with the candidate fillable region is generated, via a machine learning model, using the candidate fillable region, the textual context, and the spatial context. Thereafter, a fillable form is generated using the fillable region data, the fillable form having one or more fillable regions for accepting input.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods that implement a neural network framework for interactive multi-round image generation from natural language inputs. Specifically, the disclosed systems provide an intelligent framework (i.e., a text-based interactive image generation model) that facilitates a multi-round image generation and editing workflow that comports with arbitrary input text and synchronous interaction. In particular embodiments, the disclosed systems utilize natural language feedback for conditioning a generative neural network that performs text-to-image generation and text-guided image modification. For example, the disclosed systems utilize a trained model to inject textual features from natural language feedback into a unified joint embedding space for generating text-informed style vectors. In turn, the disclosed systems can generate an image with semantically meaningful features that map to the natural language feedback.

Abstract: Systems and methods for image processing are described. The systems and methods include receiving a low-resolution image; generating a feature map based on the low-resolution image using an encoder of a student network, wherein the encoder of the student network is trained based on comparing a predicted feature map from the encoder of the student network and a fused feature map from a teacher network, and wherein the fused feature map represents a combination of first feature map from a high-resolution encoder of the teacher network and a second feature map from a low-resolution encoder of the teacher network; and decoding the feature map to obtain prediction information for the low-resolution image.

Abstract: Systems and methods for performing Document Visual Question Answering tasks are described. A document and query are received. The document encodes document tokens and the query encodes query tokens. The document is segmented into nested document sections, lines, and tokens. A nested structure of tokens is generated based on the segmented document. A feature vector for each token is generated. A graph structure is generated based on the nested structure of tokens. Each graph node corresponds to the query, a document section, a line, or a token. The node connections correspond to the nested structure. Each node is associated with the feature vector for the corresponding object. A graph attention network is employed to generate another embedding for each node. These embeddings are employed to identify a portion of the document that includes a response to the query. An indication of the identified portion of the document is be provided.

Abstract: The technology described includes methods for pretraining a document encoder model based on multimodal self cross-attention. One method includes receiving image data that encodes a set of pretraining documents. A set of sentences is extracted from the image data. A bounding box for each sentence is generated. For each sentence, a set of predicted features is generated by using an encoder machine-learning model. The encoder model performs cross-attention between a set of masked-textual features for the sentence and a set of masked-visual features for the sentence. The set of masked-textual features is based on a masking function and the sentence. The set of masked-visual features is based on the masking function and the corresponding bounding box. A document-encoder model is pretrained based on the set of predicted features for each sentence and pretraining tasks. The pretraining tasks includes masked sentence modeling, visual contrastive learning, or visual-language alignment.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and efficiently learning parameters of a distilled neural network from parameters of a source neural network utilizing multiple augmentation strategies. For example, the disclosed systems can generate lightly augmented digital images and heavily augmented digital images. The disclosed systems can further learn parameters for a source neural network from the lightly augmented digital images. Moreover, the disclosed systems can learn parameters for a distilled neural network from the parameters learned for the source neural network. For example, the disclosed systems can compare classifications of heavily augmented digital images generated by the source neural network and the distilled neural network to transfer learned parameters from the source neural network to the distilled neural network via a knowledge distillation loss function.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generate a natural language model that provides user-entity differential privacy. For example, in one or more embodiments, the disclosed systems sample sensitive data points from a natural language dataset. Using the sampled sensitive data points, the disclosed systems determine gradient values corresponding to the natural language model. Further, the disclosed systems generate noise for the natural language model. The disclosed systems generate parameters for the natural language model using the gradient values and the noise, facilitating simultaneous protection of the users and sensitive entities associated with the natural language dataset. In some implementations, the disclosed systems generate the natural language model through an iterative process (e.g., by iteratively modifying the parameters).

Abstract: One example method involves operations for a processing device that include receiving, by a machine learning model trained to generate a search result, a search query for a text input. The machine learning model is trained by receiving pre-training data that includes multiple documents. Pre-training the machine learning model by generating, using an encoder, feature embeddings for each of the documents included in the pre-training data. The feature embeddings are generated by applying a masking function to visual and textual features in the documents. Training the machine learning model also includes generating, using the feature embeddings, output features for the documents by concatenating the feature embeddings and applying a non-linear mapping to the feature embeddings. Training the machine learning model further includes applying a linear classifier to the output features. Additionally, operations include generating, for display, a search result using the machine learning model based on the input.