Ancestry.com Operations Inc.

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.

Described herein are systems, methods, and other techniques for extracting one or more keyphrases from an input text. The input text may include a plurality of words. A plurality of token-level attention matrices may be generated using a transformer-based machine learning model. The plurality of token-level attention matrices may be converted into a plurality of word-level attention matrices. A set of candidate phrases may be identified from the plurality of words based on the plurality of word-level attention matrices. The one or more keyphrases may be selected from the set of candidate phrases.

Systems and methods for transforming and navigating historical map images are presented. The systems and methods embodiments facilitate providing, searching for, retrieving, transforming, and/or navigating a historical map image vis-à-vis a modern location and/or map. A map interface facilitates automatedly overlaying, annotating, and aligning a historical map image(s) with a modern map, allowing a user to search for a location and see the same in the historical map image, and change a visibility of the overlaid and aligned map images relative to each other. The map interface provides user interactions that facilitate retrieving, viewing, and manipulating records, historical districts, and other pertinent data through interacting with a particular location and/or searched-for individual, such as an ancestor or other person of interest.

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.

Systems, methods, and other techniques for genealogical entity resolution. In some embodiments, first tree data and second tree data are obtained, the first tree data corresponding to a first tree person and the second tree data corresponding to a second tree person. A set of features is extracted from the first tree data and the second tree data. An individual-level similarity score for each possible pairing of tree persons is generated based on the set of features. A set of most-similar tree persons is identified based on the individual-level similarity score for each possible pairing. A plurality of individual-level similarity vectors for the set of most-similar tree persons are provided 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.

OCR-text correction system and method embodiments are described. The OCR-text correction embodiments comprise or cooperate with a transformer-based sequence-to-sequence language model. The model is pretrained to denoise corrupted text and is fine-tuned using OCR-correction-specific examples. Text obtained at least in part through OCR is applied to the fine-tuned pretrained transformer model to detect at least one error in a subset of the text. Responsive to detecting the at least one error, the fine-tuned pretrained transformer model outputs an updated subset of the text to correct the at least one error.

Systems and methods for determining whether two tree persons in a genealogical database correspond to the same real-life individual. Embodiments include identifying two tree persons in a genealogical database and extracting a plurality of features from both tree persons to generate two vectors. Embodiments also include calculating a plurality of metrics between the two vectors to generate a metric function. Embodiments further include generating feature weights using a recursive process based on training data input by external users, and generating a score by calculating a weighted sum of the metric function being weighted by the feature weights. The generated score may then be compared to a threshold value.

Methods, systems, and computer-program products for image enhancement include receiving an image and optionally a user request, classify the image, crop image components of the image, restore cropped image components of the image, colorized restored image components, and reconstruct the image from the colorized, restored image components and other components. The other components may include text components that are restored in a separate treatment pipeline.

A computing server may receive genealogical records that include historical records of deceased individuals. The computing server may normalize the genealogical records into normalized genealogical records. Normalizing the genealogical records may include converting a text string of a genealogical record into a standardized format. The computing server may stitch the normalized genealogical records into a plurality of clusters. Each cluster corresponds to an individual and includes one or more genealogical records associated with the individual. The computing server may identify a life-event record that is commonly associated with a subset of clusters, the life-event record indicating that a plurality of deceased individuals are connected through a non-familial relationship in a life event documented by the life-event record. The computing server may cause a graphical user interface to display a representation of a historical network among the plurality of deceased individuals that are connected through the non-familial relationship.

A computer-implemented method for identifying an ancestor comprises segmenting a face image from an image associated with a user, providing the segmented face image to an ancestor-recognition cluster database, identifying a cluster of the ancestor-recognition cluster database comprising an image matching the segmented face image, and outputting media form the identified cluster to the user. The images may be determined to match using a suitable facial-recognition modality. Face images are compared to images corresponding to clusters that are determined to represent deceased individuals. The clusters are determined to represent deceased individuals by assessing the metadata and/or contents of the cluster to evaluate confidence that a death event has occurred.