{"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-adversarial-nets-for-multiple-text","title":"Generative Adversarial Nets for Multiple Text Corpora","arxiv_id":"1712.09127","date":"2017-12-25","proceeding":null,"authors":["Baiyang Wang","Diego Klabjan"],"abstract":"Generative adversarial nets (GANs) have been successfully applied to the\nartificial generation of image data. In terms of text data, much has been done\non the artificial generation of natural language from a single corpus. We\nconsider multiple text corpora as the input data, for which there can be two\napplications of GANs: (1) the creation of consistent cross-corpus word\nembeddings given different word embeddings per corpus; (2) the generation of\nrobust bag-of-words document embeddings for each corpora. We demonstrate our\nGAN models on real-world text data sets from different corpora, and show that\nembeddings from both models lead to improvements in supervised learning\nproblems.","url_abs":"http://arxiv.org/abs/1712.09127v1","url_pdf":"http://arxiv.org/pdf/1712.09127v1.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-adversarial-nets-for-multiple-text","repo_url":"https://github.com/baiyangwang/emgan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"cross-corpus","task_name":"Cross-corpus"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}