Collocational bootstrapping: A hypothesis about the learning of subject-verb agreement in humans and neural networks
Quick Take
The study proposes collocational bootstrapping as a mechanism for learning subject-verb agreement in language acquisition.
Key Points
- Collocational bootstrapping aids syntax acquisition.
- Neural networks simulate language learning with varied data.
- Child-directed language supports robust generalization.
📖 Reader Mode
~2 min readAbstract:In what ways might statistical signals in linguistic input assist with the acquisition of syntax? Here we hypothesize a mechanism called collocational bootstrapping, in which regularities in word co-occurrence patterns can provide cues to syntactic dependencies. We investigate whether this mechanism can support the acquisition of English subject-verb agreement. First, we simulate language acquisition by training neural networks on synthetic datasets that vary in how predictable their subject-verb pairings are. We find that there is a range of variability levels at which these statistical learners robustly learn subject-verb agreement. We then analyze the variability of subject-verb pairings in child-directed language, and we find that the variability in such data falls within the range that supported robust generalization in our computational simulations. Taken together, these results suggest that collocational bootstrapping is a viable learning strategy for the type of input that children receive.
| Comments: | Accepted to CoNLL |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.20529 [cs.CL] |
| (or arXiv:2605.20529v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2605.20529 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Claire Hobbs [view email]
[v1]
Tue, 19 May 2026 22:05:05 UTC (1,399 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →arXiv cs.CL·Leyao Wang, Yanan He, Peng Chen, Asaf Yehudai, Yixin Liu, Rex Ying, Michal Shmueli-Scheuer, Arman Cohan
1d ago FeaturedOriginal
Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?
AI Summary
The reliability of LLM judges for evaluating deep research agents is critically assessed using the REFLECT benchmark.