CHILDES
PulseAugur coverage of CHILDES — every cluster mentioning CHILDES across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New method uses GPT2 to model telicity acquisition in children
Researchers have developed a new method called Difference in Surprisal to automatically label telicity in English CHILDES corpora, distinguishing between bounded and unbounded events. This method uses GPT2 token surpris…
-
Child-like AI models reveal structural alignment boosts grammar learning
Researchers utilized child-like language models, specifically GPT-2 style models, to investigate the impact of different caregiver feedback types on grammar learning. The models were fine-tuned using reinforcement learn…
-
New toolkit enhances syntactic analysis of child-adult language interactions
Researchers have developed a new open-source toolkit called CAIT, designed to improve the syntactic analysis of child-adult interactions within the CHILDES corpus. This toolkit includes a specialized dependency parser t…
-
New System Quantifies Language Input for Children
Researchers have developed a system to automatically identify and quantify filler-gap dependencies in child language acquisition data. This system analyzes three core constructions in spoken English corpora, distinguish…
-
New toolkit CAIT enhances syntactic analysis of child-adult language interactions
Researchers have developed CAIT, a new open-source toolkit designed to analyze the syntactic structure of child-adult interactions within the CHILDES dataset. This toolkit includes a state-of-the-art dependency parser t…