collaborators

6 papers

cs.CL2025

What is the Best Sequence Length for BABYLM?

Suchir Salhan, Richard Diehl Martinez, Zébulon Goriely +1

Transformer language models typically operate with a fixed-length context window, which has grown in step with large-scale pretraining datasets. In the BabyLM Challenge, however, m…

cs.CL2025

ByteSpan: Information-Driven Subword Tokenisation

Zébulon Goriely, Suchir Salhan, Pietro Lesci +2

Recent dynamic tokenisation methods operate directly on bytes and pool their latent representations into patches. This bears similarities to computational models of word segmentati…

cs.CL2025

BabyLM's First Words: Word Segmentation as a Phonological Probing Task

Zébulon Goriely, Paula Buttery

Language models provide a key framework for studying linguistic theories based on prediction, but phonological analysis using large language models (LLMs) is difficult; there are f…

cs.CL2025

IPA-CHILDES & G2P+: Feature-Rich Resources for Cross-Lingual Phonology and Phonemic Language Modeling

Zébulon Goriely, Paula Buttery

In this paper, we introduce two resources: (i) G2P+, a tool for converting orthographic datasets to a consistent phonemic representation; and (ii) IPA CHILDES, a phonemic dataset o…

cs.CL2024

From Babble to Words: Pre-Training Language Models on Continuous Streams of Phonemes

Zébulon Goriely, Richard Diehl Martinez, Andrew Caines +2

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 ca…

cs.CL2024

Mitigating Frequency Bias and Anisotropy in Language Model Pre-Training with Syntactic Smoothing

Richard Diehl Martinez, Zebulon Goriely, Andrew Caines +2

Language models strongly rely on frequency information because they maximize the likelihood of tokens during pre-training. As a consequence, language models tend to not generalize…