{"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/a-generalized-language-model-as-the","title":"A Generalized Language Model as the Combination of Skipped n-grams and Modified Kneser-Ney Smoothing","arxiv_id":"1404.3377","date":"2014-04-13","proceeding":null,"authors":["Rene Pickhardt","Thomas Gottron","Martin Körner","Paul Georg Wagner","Till Speicher","Steffen Staab"],"abstract":"We introduce a novel approach for building language models based on a\nsystematic, recursive exploration of skip n-gram models which are interpolated\nusing modified Kneser-Ney smoothing. Our approach generalizes language models\nas it contains the classical interpolation with lower order models as a special\ncase. In this paper we motivate, formalize and present our approach. In an\nextensive empirical experiment over English text corpora we demonstrate that\nour generalized language models lead to a substantial reduction of perplexity\nbetween 3.1% and 12.7% in comparison to traditional language models using\nmodified Kneser-Ney smoothing. Furthermore, we investigate the behaviour over\nthree other languages and a domain specific corpus where we observed consistent\nimprovements. Finally, we also show that the strength of our approach lies in\nits ability to cope in particular with sparse training data. Using a very small\ntraining data set of only 736 KB text we yield improvements of even 25.7%\nreduction of perplexity.","url_abs":"http://arxiv.org/abs/1404.3377v1","url_pdf":"http://arxiv.org/pdf/1404.3377v1.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":"a-generalized-language-model-as-the","repo_url":"https://github.com/renepickhardt/generalized-language-modeling-toolkit","is_official":1,"mentioned_in_paper":1,"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":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}