{"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/from-babble-to-words-pre-training-language","title":"From Babble to Words: Pre-Training Language Models on Continuous Streams of Phonemes","arxiv_id":"2410.22906","date":"2024-10-30","proceeding":null,"authors":["Zébulon Goriely","Richard Diehl Martinez","Andrew Caines","Lisa Beinborn","Paula Buttery"],"abstract":"Language models are typically trained on large corpora of text in their default orthographic form. However, this is not the only option; representing data as streams of phonemes can offer unique advantages, from deeper insights into phonological language acquisition to improved performance on sound-based tasks. The challenge lies in evaluating the impact of phoneme-based training, as most benchmarks are also orthographic. To address this, we develop a pipeline to convert text datasets into a continuous stream of phonemes. We apply this pipeline to the 100-million-word pre-training dataset from the BabyLM challenge, as well as to standard language and grammatical benchmarks, enabling us to pre-train and evaluate a model using phonemic input representations. Our results show that while phoneme-based training slightly reduces performance on traditional language understanding tasks, it offers valuable analytical and practical benefits.","url_abs":"https://arxiv.org/abs/2410.22906v1","url_pdf":"https://arxiv.org/pdf/2410.22906v1.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":"from-babble-to-words-pre-training-language","repo_url":"https://github.com/codebyzeb/Corpus-Phonemizer","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"language-acquisition","task_name":"Language Acquisition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.22906","atlas_url":"https://app.syntology.ai/?focus=2410.22906","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}