{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/generative-concatenative-nets-jointly-learn","title":"Generative Concatenative Nets Jointly Learn to Write and Classify Reviews","arxiv_id":"1511.03683","date":"2015-11-11","proceeding":null,"authors":["Zachary C. Lipton","Sharad Vikram","Julian McAuley"],"abstract":"A recommender system's basic task is to estimate how users will respond to\nunseen items. This is typically modeled in terms of how a user might rate a\nproduct, but here we aim to extend such approaches to model how a user would\nwrite about the product. To do so, we design a character-level Recurrent Neural\nNetwork (RNN) that generates personalized product reviews. The network\nconvincingly learns styles and opinions of nearly 1000 distinct authors, using\na large corpus of reviews from BeerAdvocate.com. It also tailors reviews to\ndescribe specific items, categories, and star ratings. Using a simple input\nreplication strategy, the Generative Concatenative Network (GCN) preserves the\nsignal of static auxiliary inputs across wide sequence intervals. Without any\nadditional training, the generative model can classify reviews, identifying the\nauthor of the review, the product category, and the sentiment (rating), with\nremarkable accuracy. Our evaluation shows the GCN captures complex dynamics in\ntext, such as the effect of negation, misspellings, slang, and large\nvocabularies gracefully absent any machinery explicitly dedicated to the\npurpose.","url_abs":"http://arxiv.org/abs/1511.03683v5","url_pdf":"http://arxiv.org/pdf/1511.03683v5.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"generative-concatenative-nets-jointly-learn","repo_url":"https://github.com/pushpakrajgautam/DateGenWeb","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"negation","task_name":"Negation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1511.03683","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}