Amazon Technologies, Inc.

Benjamin Thomas Cohen

Grant Michael Emery

Vijai Mohan

Roshan Harish Makhijani

Scott Allen Mongrain

Logan Luyet Dillard

Rahul H Bhagat

Madhu Madhava Kurup

Adam Callahan Sanders

Brian Cameros

Yongwen Liang

Eli Glen Rosofsky

Michael David Quinn

Features are disclosed for identifying randomized latent feature language modeling, such as a recurrent neural network language modeling (RNNLM). Sequences of item identifiers may be provided as the language for training the language model where the item identifiers are the words of the language. To avoid localization bias, the sequences may be randomized prior to or during the training process to provide more accurate prediction models.

Randomized latent feature learning

Features are disclosed for identifying and routing items for tagging using a latent feature model, such as a recurrent neural network language model (RNNLM). The model may be trained to identify latent features for catalog items such as movies, books, food items, beverages, and the like. Based on similarities in latent features, tags previous assigned to items may be applied to untagged items. Application may be manual or automatic. In either case, resources need to be balances to ensure efficient tagging of items. The included features help to identify and direct these limited tagging resources.

Latent feature based tag routing

The present technology may identify item category affinities by identifying a plurality of classifications of an item. An accuracy of the plurality of classifications relative to one another for the item may be identified. A category affinity of the item may be determined based on the accuracy of the plurality of classifications relative to one another.

Video classification

Growing community of inventors

Seattle, WA, United States of America

Benjamin Thomas Cohen