Amazon Technologies, Inc.

Karim Bouyarmane

Ismail Baha Tutar

Amirhossein Tavanaei

The present disclosure presents a generative model configured to receive input regarding an item in two different modalities, such as text data and non-text data (including, for example, image or audio data), in order to generate output regarding the item that is determined based on a combination of both modalities' input. Specific relative positional and token type embeddings may be employed in an encoder portion of an encoder-decoder arrangement. An associated decoder may be trained to generate new text corresponding to diverse tasks based on the encoded representation of the two inputs as generated within the encoder. For example, the decoder may be utilized to generate attributes regarding the input item, auto-complete or auto-correct a title or description of the item, among other uses.

Multimodal input to text transformer

A hierarchical embedding model is used to obtain respective language-agnostic embeddings of entity records of a cross-language data set. A plurality of record representation pairs is prepared based at least in part on the language-agnostic embeddings. A machine learning model is trained using the record representations pairs to generate similarity scores for pairs of entity records whose text attributes are expressed in different languages.

Artificial intelligence system for translation-less similarity analysis in multi-language contexts

Systems and methods are provided for using language-agnostic embedding data to analyze a plurality of items associated with an item identifier in a catalog and determine a characteristic associated with the plurality of items or the item identifier. A distribution may be generated based on the language-agnostic embedding data and groups of items may be identified based on the distribution. Based on the groups of items, the item identifier may be classified as a consistent item identifier or an inconsistent item identifier across the catalog. A primary group of items and secondary groups of items can be identified for the plurality of items. The primary group of items may include items with a verified association with the item identifier and the secondary groups of items may include items with an unverified association with the item identifier.

Growing community of inventors

Seattle, WA, United States of America

Karim Bouyarmane