{"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/fast-small-and-exact-infinite-order-language","title":"Fast, Small and Exact: Infinite-order Language Modelling with Compressed Suffix Trees","arxiv_id":"1608.04465","date":"2016-08-16","proceeding":"TACL 2016 1","authors":["Ehsan Shareghi","Matthias Petri","Gholamreza Haffari","Trevor Cohn"],"abstract":"Efficient methods for storing and querying are critical for scaling\nhigh-order n-gram language models to large corpora. We propose a language model\nbased on compressed suffix trees, a representation that is highly compact and\ncan be easily held in memory, while supporting queries needed in computing\nlanguage model probabilities on-the-fly. We present several optimisations which\nimprove query runtimes up to 2500x, despite only incurring a modest increase in\nconstruction time and memory usage. For large corpora and high Markov orders,\nour method is highly competitive with the state-of-the-art KenLM package. It\nimposes much lower memory requirements, often by orders of magnitude, and has\nruntimes that are either similar (for training) or comparable (for querying).","url_abs":"http://arxiv.org/abs/1608.04465v1","url_pdf":"http://arxiv.org/pdf/1608.04465v1.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":"fast-small-and-exact-infinite-order-language","repo_url":"https://github.com/eehsan/cstlm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"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":{"syntology_url":"https://syntology.ai/paper/1608.04465","atlas_url":"https://app.syntology.ai/?focus=1608.04465","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}