Abstract: A method for identifying the presence of a logo in an image includes providing a neural network having an image encoder, a text encoder, and a score calculator. The method includes receiving the image and a textual description associated with the logo. The method further includes providing the image to the image encoder and the textual description to the text encode. The method includes executing the image encoder and the text encoder, wherein the image encoder generates one or more image embeddings from the image and the text encoder generates one or more text embeddings from the textual description. The method further includes executing the score calculator, wherein the score calculator generates a score from the one or more image embeddings and the one or more text embeddings. The method also includes determining the presence of the logo in the image based on the score.

Abstract: Methods and apparatuses are described for generating parallel synthetic training data for a machine learning model. A server computing device generates a model training dataset from a baseline dataset comprising a plurality of sentences labeled as noncompliant with a ruleset. The server trains a conditional autoregressive language model using the model training dataset as input to generate a corpus of synthetic predicted to be noncompliant with the rulesets. For each synthetic sentence, the server executes a compliance classification model to generate a compliance label for the synthetic sentence. The server identifies a plurality of the synthetic sentences labeled as noncompliant that are semantically similar to sentences from the baseline dataset to generate a first parallel corpus of synthetic training data. The server executes a language suggestion model using the identified synthetic sentences to generate a second parallel corpus of synthetic training data.

Abstract: Methods and apparatuses are described for predicting compliance of text documents with a ruleset using self-supervised machine learning. A server executes an NLP teacher model on first unlabeled sentences to generate a first compliance pseudo-label for each first unlabeled sentence. The server trains an NLP student model using the first unlabeled sentences and first compliance pseudo-labels, including injecting input noise by aggregating each unlabeled sentence with one or more sentences adjacent to each unlabeled sentence into a sentence block and providing the aggregated sentence blocks as input to train the NLP student model. The server executes the trained NLP student model, using second unlabeled sentences, to generate a second compliance pseudo-label for each second unlabeled sentence. The server determines compliance of the second sentences with one or more rulesets using the second compliance pseudo-labels.