CAIT: A Syntactic Parsing Toolkit for Child-Adult InTeractions

2026-05-19

AI Summary

This study addresses the poor performance of existing general-purpose syntactic parsers on CHILDES child–adult interaction corpora. To bridge this gap, the authors present the first open-source dependency parser specifically designed for child language acquisition research, built upon the UD-English-CHILDES treebank. The system integrates part-of-speech tagging and construction labeling within the Universal Dependencies framework. Evaluated on CHILDES data, it significantly outperforms general-purpose parsers such as SpaCy and Stanza. By providing high-precision, domain-tailored syntactic analysis, this tool enables large-scale, reproducible studies of syntactic development and establishes a robust computational infrastructure for research in child language acquisition.

Abstract

CHILDES is a paramount resource for language acquisition studies -- yet computational tools for analyzing its syntactic structure remain limited. Leveraging the recent release of the UD-English-CHILDES treebank with gold-standard Universal Dependencies (UD) annotations, we train a state-of-the-art dependency parser specifically tailored to CHILDES. The parser more accurately captures syntactic patterns in child--adult interactions, outperforming widely used off-the-shelf English parsers, including SpaCy and Stanza. Alongside the parser, we also release a Part-of-Speech tagger and an utterance-level construction tagger, which together form the open-source Syntactic Parsing Toolkit for Child--Adult InTeractions (CAIT). Through a detailed error analysis and a case study tracking the distribution of syntactic constructions across developmental time in CHILDES, we demonstrate the practical utility of the toolkit for large-scale, reproducible research on language acquisition.

Problem

• CHILDES
• syntactic parsing
• language acquisition
• child-adult interaction
• Universal Dependencies

Innovation

• dependency parsing
• CHILDES
• Universal Dependencies
• language acquisition
• syntactic toolkit