Pinterest, Inc.

Heath Vinicombe

Yunsong Guo

Yu Liu

Chenyi Li

Anant Srinivas Subramanian

Systems and methods are presented for inferring an embedding vector of an item of a first type into the embedding space. Upon receiving a first time for which there is no embedding vector, documents of a document corpus that include (co-occurrence) both the received item and other items of the same type are identified. Of those other items that have embedding vectors, those embedding vectors are retrieved and averaged. The resulting averaged embedding vector is established as an inferred embedding vector for the received item.

Embedding inference

Determining emebedding vectors for an unmapped content item using embedding inferenece

Systems and methods are set forth for identifying key-words and key-phrases, collectively referred to as key-terms, from a document. A document is accessed and the document is tokenized, each token corresponding to a word or phrase occurring within the document. Term frequencies of the terms of the tokens may be determined and TF-IDF scores may be generated according to the term frequencies. Embedding vectors for the terms of the tokens may be generated and a document embedding vector may be generated according to the embedding vectors of the documents. A similarity score may be determined for each token according to the embedding vector of a token and the document embedding vector. Additionally, an overall score may be determined for each token according to the term of the token, a TF-IDF score, similarity scores, and the like. Terms from the highest scoring tokens are selected as the key-terms for the document.

Growing community of inventors

San Francisco, CA, United States of America

Heath Vinicombe