Abstract: Embodiments are provided that include generating, by an inter-modal predictor, predicted second-mode information for a first text-based record based on first-mode information of the first text-based record. Embodiments also include generating a first value by evaluating a first loss function that is based on a first difference between the second-mode information of the first text-based record as predicted and as observed; updating the inter-modal predictor based on the first value; generating, by the updated inter-modal predictor, predicted second-mode information for a second text-based record in the database based on first-mode information of the second text-based record; generating a second value by evaluating a second loss function that is based on a second difference between the second-mode information of the second text-based record as predicted and as observed; and training an operational model based on the second value.

Abstract: Techniques are disclosed herein that are directed towards using satellite image data to narrow down the search space for statistically significant and/or meaningful ground truth data. Various implementations include techniques for labeling agricultural image data using unsupervised clustering and/or active learning techniques. Additional or alternative implementations include collecting more detailed crop information from locations on the ground with a higher quality (e.g., especially representative of a particular crop) ground truth.

Abstract: There is provided a method and a system for recommending a given text candidate as a value for a field. A document image is received and a set of text boxes are detected using optical character recognition, each of the set of text boxes comprising a respective character sequence. For each text box, based on at least the respective character sequence, at least one respective text candidate is generated to thereby obtain a set of text candidates. At least one feature extractor is used to generate a respective candidate feature vector based on each respective text candidate. An indication of the field is received, and a respective candidate score indicative of a relevance of the respective text candidate is determined. In response to a given candidate score being above a threshold, the given text candidate associated with the given candidate score is output as a recommendation for the field.

Abstract: Embodiments are provided that include generating, by an inter-modal predictor, predicted second-mode information for a first text-based record based on first-mode information of the first text-based record. Embodiments also include generating a first value by evaluating a first loss function that is based on a first difference between the second-mode information of the first text-based record as predicted and as observed; updating the inter-modal predictor based on the first value; generating, by the updated inter-modal predictor, predicted second-mode information for a second text-based record in the database based on first-mode information of the second text-based record; generating a second value by evaluating a second loss function that is based on a second difference between the second-mode information of the second text-based record as predicted and as observed; and training an operational model based on the second value.