From Linear Input to Hierarchical Structure: Function Words as Statistical Cues for Language Learning
This addresses a foundational question in language acquisition for computational linguistics, though it is incremental in building on existing theories about function words.
The paper tackled the problem of how statistical properties of function words support learning hierarchical structure from linear input, finding through cross-linguistic analysis and neural modeling that frequency and structural association are key cues, with variants preserving these properties being more easily acquired.
What statistical conditions support learning hierarchical structure from linear input? In this paper, we address this question by focusing on the statistical distribution of function words. Function words have long been argued to play a crucial role in language acquisition due to their distinctive distributional properties, including high frequency, reliable association with syntactic structure, and alignment with phrase boundaries. We use cross-linguistic corpus analysis to first establish that all three properties are present across 186 studied languages. Next, we use a combination of counterfactual language modeling and ablation experiments to show that language variants preserving all three properties are more easily acquired by neural learners, with frequency and structural association contributing more strongly than boundary alignment. Follow-up probing and ablation analyses further reveal that different learning conditions lead to systematically different reliance on function words, indicating that similar performance can arise from distinct internal mechanisms.