From Babble to Words: Pre-Training Language Models on Continuous Streams of Phonemes
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929568562020352 |
|---|---|
| author | Goriely, Zébulon Martinez, Richard Diehl Caines, Andrew Beinborn, Lisa Buttery, Paula |
| author_facet | Goriely, Zébulon Martinez, Richard Diehl Caines, Andrew Beinborn, Lisa Buttery, Paula |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_22906 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | From Babble to Words: Pre-Training Language Models on Continuous Streams of Phonemes Goriely, Zébulon Martinez, Richard Diehl Caines, Andrew Beinborn, Lisa Buttery, Paula Computation and Language 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. |
| title | From Babble to Words: Pre-Training Language Models on Continuous Streams of Phonemes |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2410.22906 |