{"_id":"FtHrPaqQ6gSTdpt5E","bibbaseid":"vasile-smirnova-conneau-metaprod2vecproductembeddingsusingsideinformationforrecommendation-2016","authorIDs":[],"author_short":["Vasile, F.","Smirnova, E.","Conneau, A."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"New York, NY, USA","series":"RecSys '16","title":"Meta-Prod2Vec: Product Embeddings Using Side-Information for Recommendation","isbn":"978-1-4503-4035-9","shorttitle":"Meta-Prod2Vec","url":"http://doi.acm.org/10.1145/2959100.2959160","doi":"10.1145/2959100.2959160","abstract":"We propose Meta-Prod2vec, a novel method to compute item similarities for recommendation that leverages existing item metadata. Such scenarios are frequently encountered in applications such as content recommendation, ad targeting and web search. Our method leverages past user interactions with items and their attributes to compute low-dimensional embeddings of items. Specifically, the item metadata is injected into the model as side information to regularize the item embeddings. We show that the new item representations lead to better performance on recommendation tasks on an open music dataset.","urldate":"2017-04-05","booktitle":"Proceedings of the 10th ACM Conference on Recommender Systems","publisher":"ACM","author":[{"propositions":[],"lastnames":["Vasile"],"firstnames":["Flavian"],"suffixes":[]},{"propositions":[],"lastnames":["Smirnova"],"firstnames":["Elena"],"suffixes":[]},{"propositions":[],"lastnames":["Conneau"],"firstnames":["Alexis"],"suffixes":[]}],"year":"2016","keywords":"embeddings, neural networks, recommender systems, word2vec","pages":"225–232","bibtex":"@inproceedings{vasile_meta-prod2vec:_2016,\n\taddress = {New York, NY, USA},\n\tseries = {{RecSys} '16},\n\ttitle = {Meta-{Prod2Vec}: {Product} {Embeddings} {Using} {Side}-{Information} for {Recommendation}},\n\tisbn = {978-1-4503-4035-9},\n\tshorttitle = {Meta-{Prod2Vec}},\n\turl = {http://doi.acm.org/10.1145/2959100.2959160},\n\tdoi = {10.1145/2959100.2959160},\n\tabstract = {We propose Meta-Prod2vec, a novel method to compute item similarities for recommendation that leverages existing item metadata. Such scenarios are frequently encountered in applications such as content recommendation, ad targeting and web search. Our method leverages past user interactions with items and their attributes to compute low-dimensional embeddings of items. Specifically, the item metadata is injected into the model as side information to regularize the item embeddings. We show that the new item representations lead to better performance on recommendation tasks on an open music dataset.},\n\turldate = {2017-04-05},\n\tbooktitle = {Proceedings of the 10th {ACM} {Conference} on {Recommender} {Systems}},\n\tpublisher = {ACM},\n\tauthor = {Vasile, Flavian and Smirnova, Elena and Conneau, Alexis},\n\tyear = {2016},\n\tkeywords = {embeddings, neural networks, recommender systems, word2vec},\n\tpages = {225--232}\n}\n\n","author_short":["Vasile, F.","Smirnova, E.","Conneau, A."],"key":"vasile_meta-prod2vec:_2016","id":"vasile_meta-prod2vec:_2016","bibbaseid":"vasile-smirnova-conneau-metaprod2vecproductembeddingsusingsideinformationforrecommendation-2016","role":"author","urls":{"Paper":"http://doi.acm.org/10.1145/2959100.2959160"},"keyword":["embeddings","neural networks","recommender systems","word2vec"],"downloads":0},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/jsan","creationDate":"2020-05-26T09:25:38.366Z","downloads":0,"keywords":["embeddings","neural networks","recommender systems","word2vec"],"search_terms":["meta","prod2vec","product","embeddings","using","side","information","recommendation","vasile","smirnova","conneau"],"title":"Meta-Prod2Vec: Product Embeddings Using Side-Information for Recommendation","year":2016,"dataSources":["h8ZDyzMApwwGDDKcf"]}