Papers by Sanghoun Song
Do BabyLMs Wanna Learn Wanna Contraction? On the Learnability without Language-Specific Bias (2026.findings-acl)
Copied to clipboard
| Challenge: | grammatical constraints on wanna contraction can be learned by artificial learners under cognitively plausible learning conditions. |
| Approach: | They evaluate 24 BabyLMs from 2024 BabyLM Challenge and four standard models . they find that only encoder-based BabyLM models can capture wanna contraction . |
| Outcome: | The proposed models show modest but meaningful sensitivity on large datasets and high-frequency wanna instances. |