{"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/author-identification-using-multi-headed","title":"Author Identification using Multi-headed Recurrent Neural Networks","arxiv_id":"1506.04891","date":"2015-06-16","proceeding":null,"authors":["Douglas Bagnall"],"abstract":"Recurrent neural networks (RNNs) are very good at modelling the flow of text,\nbut typically need to be trained on a far larger corpus than is available for\nthe PAN 2015 Author Identification task. This paper describes a novel approach\nwhere the output layer of a character-level RNN language model is split into\nseveral independent predictive sub-models, each representing an author, while\nthe recurrent layer is shared by all. This allows the recurrent layer to model\nthe language as a whole without over-fitting, while the outputs select aspects\nof the underlying model that reflect their author's style. The method proves\ncompetitive, ranking first in two of the four languages.","url_abs":"http://arxiv.org/abs/1506.04891v2","url_pdf":"http://arxiv.org/pdf/1506.04891v2.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":"author-identification-using-multi-headed","repo_url":"https://github.com/pan-webis-de/caravel","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"author-identification-using-multi-headed","repo_url":"https://github.com/ShogoAkiyama54/author-identification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"author-identification-using-multi-headed","repo_url":"https://github.com/ShogoAkiyama54/author_identification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"author-identification-using-multi-headed","repo_url":"https://github.com/shogo54/author-identification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1506.04891","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}