{"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/ensemble-of-generative-and-discriminative","title":"Ensemble of Generative and Discriminative Techniques for Sentiment Analysis of Movie Reviews","arxiv_id":"1412.5335","date":"2014-12-17","proceeding":null,"authors":["Grégoire Mesnil","Tomas Mikolov","Marc'Aurelio Ranzato","Yoshua Bengio"],"abstract":"Sentiment analysis is a common task in natural language processing that aims\nto detect polarity of a text document (typically a consumer review). In the\nsimplest settings, we discriminate only between positive and negative\nsentiment, turning the task into a standard binary classification problem. We\ncompare several ma- chine learning approaches to this problem, and combine them\nto achieve the best possible results. We show how to use for this task the\nstandard generative lan- guage models, which are slightly complementary to the\nstate of the art techniques. We achieve strong results on a well-known dataset\nof IMDB movie reviews. Our results are easily reproducible, as we publish also\nthe code needed to repeat the experiments. This should simplify further advance\nof the state of the art, as other researchers can combine their techniques with\nours with little effort.","url_abs":"http://arxiv.org/abs/1412.5335v7","url_pdf":"http://arxiv.org/pdf/1412.5335v7.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":"ensemble-of-generative-and-discriminative","repo_url":"https://github.com/mesnilgr/iclr15","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"ensemble-of-generative-and-discriminative","repo_url":"https://github.com/libofang/DV-ngram","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"ensemble-of-generative-and-discriminative","repo_url":"https://github.com/sidaw/nbsvm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"ensemble-of-generative-and-discriminative","repo_url":"https://github.com/yurayli/imdb_sentiment","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"binary-classification","task_name":"Binary Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1412.5335","atlas_url":"https://app.syntology.ai/?focus=1412.5335","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}