Target Brands, Inc.

Shalin Shah

Nicholas Scott Eggert

Ryan David Siskind

Ramasubbu Venkatesh

Venkataramana Bantwal Kini

Methods and systems for attributing browsing activity from two or more different network-connected devices to a single user are disclosed. In one aspect, cookies generated by the browsing activity of different unidentified devices at a website are received. A random forest classifier trained on probabilities output from a Gaussian mixture model is applied to the unidentified cookies to determine a probability that two different cookies were generated by the same user. In some embodiments, personalized content is then delivered to the user based on the characteristics of the paired cookies.

Similarity learning-based device attribution

Methods and systems for performing named entity recognition are disclosed. One method includes using a multi-task approach to fine-tune a neural network to perform named entity recognition. A multi-task objective function can include a combination of a triplet loss and a named entity recognition loss. The triplet loss can include the use of supplementary texts. The method further includes using the fine-tuned neural network to identify one or more named entities in a text. Aspects of the disclosure also include integrating named entity recognition with one or more other natural language processing tasks.

Multi-task triplet loss for named entity recognition using supplementary text

Methods and systems for performing multi-task learning of query intent and named entities are provided. One method includes receiving a query comprising query text. The method further includes providing the query text to a neural network model implemented on a computing system, the neural network model having a plurality of layers, wherein at least one layer comprises a plurality of loss functions including a named entity tag learning loss function and an intent classification loss function. The method also includes obtaining, from the neural network model, an identification of a named entity and a query intent derived from the query text. A query response may be formulated based, at least in part, on the named entity and query intent.

Multi-task learning of query intent and named entities

Methods and systems for generating link predictions are provided. In one aspect, a method includes initializing a graph including a plurality of nodes representing selections of items in a training dataset to a multivariate normal distribution having a predetermined mean and a predetermined initial variance, the items in the training dataset comprising items in an item collection. The method includes, for each node in the graph, modeling embeddings for the node as embeddings of each neighboring node having a shared edge, with each being updated based at least in part on a transition probability and a variance. A predetermined number of iterations of updating are executed each iteration including an updated variance based on a learning rate. Based on receipt of an identification of an item from among the item collection, a plurality of predicted selections of items are identified using the embeddings for a node corresponding to the item.

Growing community of inventors

Sunnyvale, CA, United States of America

Shalin Shah