Abstract: Systems, methods, and other techniques for genealogical entity resolution. The systems obtain first tree data and second tree data, the first tree data corresponding to a first tree person and the second tree data corresponding to a second tree person. The systems extract a set of features from the first tree data and the second tree data. The systems further generate an individual-level similarity score for each possible pairing of tree persons based on the set of features to identify a set of most-similar tree persons based on the individual-level similarity score for each possible pairing. The systems also provide a plurality of individual-level similarity scores for the set of most-similar tree persons as input to a family-level ML model to determine that the first tree person and the second tree person correspond to a same individual.

Abstract: Systems and methods for identifying and segmenting objects from images include a preprocessing module configured to adjust a size of a source image; a region-proposal module configured to propose one or more regions of interest in the size-adjusted source image; and a prediction module configured to predict a classification, bounding box coordinates, and mask. Such systems and methods may utilize end-to-end training of the modules using adversarial loss, facilitating the use of a small training set, and can be configured to process historical documents, such as large images comprising text. The preprocessing module within the systems and methods can utilize a conventional image scaler in tandem with a custom image scaler to provide a resized image suitable for GPU processing, and the region-proposal module can utilize a region-proposal network from a single-stage detection model in tandem with a two-stage detection model paradigm to capture substantially all particles in an image.

Abstract: Systems and methods for identifying and segmenting objects from images include a preprocessing module configured to adjust a size of a source image; a region-proposal module configured to propose one or more regions of interest in the size-adjusted source image; and a prediction module configured to predict a classification, bounding box coordinates, and mask. Such systems and methods may utilize end-to-end training of the modules using adversarial loss, facilitating the use of a small training set, and can be configured to process historical documents, such as large images comprising text. The preprocessing module within said systems and methods can utilize a conventional image scaler in tandem with a custom image scaler to provide a resized image suitable for GPU processing, and the region-proposal module can utilize a region-proposal network from a single-stage detection model in tandem with a two-stage detection model paradigm to capture substantially all particles in an image.

Abstract: Described herein are systems, methods, and other techniques for segmenting an input text. A set of tokens are extracted from the input text. Token representations are computed for the set of tokens. The token representations are provided to a machine learning model that generates a set of label predictions corresponding to the set of tokens. The machine learning model was previously trained to generate label predictions in response to being provided input token representations. Each of the set of label predictions indicates a position of a particular token of the set of tokens with respect to a particular segment. One or more segments within the input text are determined based on the set of label predictions.

Abstract: Systems, methods, and other techniques for extracting data from obituaries are provided. In some embodiments, an obituary containing a plurality of words is received. Using a machine learning model, an entity tag from a set of entity tags may be assigned to each of one or more words of the plurality of words. Each particular tag from the set of entity tags may include a relationship component and a category component. The relationship component may indicate a relationship between a particular word and the deceased individual. The category component may indicate a categorization of the particular word to a particular category from a set of categories. The extracted data may be stored in a genealogical database.

Abstract: Techniques for training a machine-learning (ML) model for captioning images are disclosed. A plurality of feature vectors and a plurality of visual attention maps are generated by a visual model of the ML model based on an input image. Each of the plurality of feature vectors correspond to different regions of the input image. A plurality of caption attention maps are generated by an attention model of the ML model based on the plurality of feature vectors. An attention penalty is calculated based on a comparison between the caption attention maps and the visual attention maps. A loss function is calculated based on the attention penalty. One or both of the visual model and the attention model are trained using the loss function.

Abstract: Augmented reality is used to display graphical elements overlaid on a continually updating image of an area around an augmented reality device (e.g., a mobile device). The graphical element may contain geographical location information about a grave of an ancestor and/or biographical information about the ancestor. The continually updating image is captured by a camera of the augmented reality device and updates in response to time and motion of the augmented reality device. Based on orientation data and geographical location data collected by the augmented reality device, the graphical element is updated and displayed on the mobile device.

Abstract: Systems and methods for classifying historical images. A feature extractor may create feature vectors corresponding to a plurality of images. A first classification of the plurality of images may be performed based on the plurality of feature vectors, which may include assigning a label to each of the plurality of images and assigning a probability for each of the assigned labels. The assigned probability for each of the assigned labels may be related to a statistical confidence that a particular assigned label is correctly assigned to a particular image. A subset of the plurality of images may be displayed to a display device. An input corresponding to replacement of an incorrect label with a corrected label for a certain image may be received from a user. A second classification of the plurality of images based on the input from the user may be performed.

Abstract: Systems and methods for training a machine learning (ML) ranking model to rank genealogy hints are described herein. One method includes retrieving a plurality of genealogy hints for a target person, where each of the plurality of genealogy hints corresponds to a genealogy item and has a hint type of a plurality of hint types. The method includes generating, for each of the plurality of genealogy hints, a feature vector having a plurality of feature values, the feature vector being included in a plurality of feature vectors. The method includes extending each of the plurality of feature vectors by at least one additional feature value based on the number of features of one or more other hint types of the plurality of hint types. The method includes training the ML ranking model using the extended plurality of feature vectors and user-provided labels.

Abstract: Image identification, retrieval, transformation and arrangement systems, methods, and computer-program products are configured to access a family tree of a user in a family tree database, identify one or more additional persons of interest in the family tree, determine whether the one or more persons of interest is associated with an image, retrieve the image, and transform the image of the one or more additional persons of interest with an image of the user or other person such as in an image arrangement template. Whether an image pertains to a person is determined using a machine learning classifier. A plurality of candidate lineages from a root or self node may be evaluated based on the number and/or quality of images associated therewith and/or based on filtering the one or more characteristics of the nodes in the candidate lineages.

Abstract: Systems, methods, and other techniques for extracting data from obituaries are provided. In some embodiments, an obituary containing a plurality of words is received. Using a machine learning model, an entity tag from a set of entity tags may be assigned to each of one or more words of the plurality of words. Each particular tag from the set of entity tags may include a relationship component and a category component. The relationship component may indicate a relationship between a particular word and the deceased individual. The category component may indicate a categorization of the particular word to a particular category from a set of categories. The extracted data may be stored in a genealogical database.

Abstract: Hybrid machine-learning systems and methods can be used to perform automatic keyphrase extraction from input text, such as historical records. For example, a computer-implemented method for extracting keyphrases from input text can include receiving input text having a plurality of words and identifying a set of candidate phrases from the plurality of words and a score for each of the candidate phrases using one or more unsupervised machine-learning models. The method can also include identifying named entities from the set of candidate phrases using one or more supervised machine-learning models and determining an updated set of scores for at least some of the candidate phrases within the set based on the named entities identified using the supervised machine-learning model. The method can also include identifying a keyphrase from the set of candidate phrases based on the updated set of scores.

Abstract: Search-result explanation systems, methods, and computer-program products receive a user search query, expand the search query into a plurality of sub-queries, perform a database search using the expanded user search query, and determine which sub-queries of the plurality of sub-queries matched with a particular search result. Results from the database search are re-indexed in an index generated on-the-fly and in-memory, within which the results are searched using the sub-queries to determine matching fields and match types. A score is determined based on the type of match(es) with a particular search result based on one or more predefined weights and normalized using a denominator comprising a fictitious, on-the-fly record configured to receive a perfect score according to the received user search query. A user interface showing ranked results and explanations for the ranking, including a score for the result based on the expanded user search query.

Abstract: Described herein are systems, methods, and other techniques for training a generative adversarial network (GAN) to perform an image-to-image transformation for recognizing text. A pair of training images are provided to the GAN. The pair of training images include a training image containing a set of characters in handwritten form and a reference training image containing the set of characters in machine-recognizable form. The GAN includes a generator and a discriminator. The generated image is generated using the generator based on the training image. Update data is generated using the discriminator based on the generated image and the reference training image. The GAN is trained by modifying one or both of the generator and the discriminator using the update data.

Abstract: Systems and methods for training a machine learning (ML) ranking model to rank genealogy hints are described herein. One method includes retrieving a plurality of genealogy hints for a target person, where each of the plurality of genealogy hints corresponds to a genealogy item and has a hint type of a plurality of hint types. The method includes generating, for each of the plurality of genealogy hints, a feature vector having a plurality of feature values, the feature vector being included in a plurality of feature vectors. The method includes extending each of the plurality of feature vectors by at least one additional feature value based on the number of features of one or more other hint types of the plurality of hint types. The method includes training the ML ranking model using the extended plurality of feature vectors and user-provided labels.

Abstract: Systems, methods, and other techniques for extracting data from obituaries are provided. In some embodiments, an obituary containing a plurality of words is received. Using a machine learning model, an entity tag from a set of entity tags may be assigned to each of one or more words of the plurality of words. Each particular tag from the set of entity tags may include a relationship component and a category component. The relationship component may indicate a relationship between a particular word and the deceased individual. The category component may indicate a categorization of the particular word to a particular category from a set of categories. The extracted data may be stored in a genealogical database.

Abstract: A search system performs a federated search across multiple databases and generates a ranked combined list of found genealogical records. The system receives a user query with one or more specified characteristics. The system may determine expanded characteristics derived from the specified characteristics. The system searches the various databases with the characteristics retrieving records according to the characteristics. The system combines the retrieved records and ranks them using a machine learning model. The machine learning model is configured to assign a weight to the records returned from each of the genealogical databases based on the characteristics specified in the user query. The machine learning model may be trained by any combination of one or more of: a Nelder-Mead method, a coordinate ascent method, and a simulated annealing method. The ranked combined results are provided in response to the user query.

Abstract: Systems and methods for retrieving a set of ordered items from a distributed database. A plurality of ordered items may be stored at a cache. The plurality of ordered items may have a length of N+B at a first instant in time. A first instruction to delete a first item of the plurality of ordered items may be received. A second instruction to add a second item to the plurality of ordered items may be received. The first instruction and the second instruction may be stored in a change log. A request for the first N items of the plurality of ordered items may be received. The first instruction may be executed by deleting the first item from the plurality of ordered items. The second instruction may be executed by adding the second item to the plurality of ordered items. The first N items of the plurality of ordered items may be sent in response to the request.

Abstract: Embodiments described herein relate generally to a methodology of efficient object classification within a visual medium. The methodology utilizes a first neural network to perform an attention based object localization within a visual medium to generate a visual mask. The visual mask is applied to the visual medium to generate a masked visual medium. The masked visual medium may be then fed into a second neural network to detect and classify objects within the visual medium.

Abstract: A method for ranking genealogical records includes using a machine learning model to rank multiple searched records based on relevancy. The relevancy may be determined by identifying features included in a record and scaling each feature by a corresponding weight factor. In addition, a method for training a machine learning model and increasing the convergence speed of the training is described. To train the model, a machine learning process is used to optimize a ranking performance metric. A set of weights corresponding to multiple features are used to rank multiple past search records in a training set. An initial set of the weights are set by the expectation values of the weights. The weights are incrementally changed to optimize the ranking performance metric. The step size of the increment is determined based on the sensitivity of the ranking performance metric relative to the step size.