TEXT-BASED IMAGE RETRIEVAL SYSTEM BY LEARNING SENTENCE EMBEDDINGS JOINTLY WITH CLICK AND TITLE DATA

Text-to-visual machine learning embedding techniques are described that overcome the challenges of conventional techniques in a variety of ways. These techniques include use of query-based training data which may expand availability and types of training data usable to train a model. Generation of negative digital image samples is also described that may increase accuracy in training the model using machine learning. A loss function is also described that also supports increased accuracy and computational efficiency by losses separately, e.g., between positive or negative sample embeddings a text embedding. Inventors: Aggarwal et al. Title: Text-to-Visual Machine Learning Embedding Techniques Receive a plurality of text queries used to initiate a plurality of digital] image searches Receive a plurality of digital images that are user selected from search results generated by the plurality of digital image searches Generate a training dataset based on the plurality of text queries and the plurality of digital images Train a model using machine learning based on a loss function using the training dataset Generate a subsequent search result using the model