Skip to content

Latest commit

 

History

History
25 lines (18 loc) · 1.62 KB

README.md

File metadata and controls

25 lines (18 loc) · 1.62 KB
Raw

Prosodic Features from Large Corpora of Child-Directed Speech as Predictors of the Age of Acquisition of Words

This repository contains code and data for the Ridge Regression analyses presented in the paper "Prosodic Features from Large Corpora of Child-Directed Speech as Predictors of the Age of Acquisition of Words (ArXiv preprint, 2017)"

Data

The data folder contains word type-level prosodic features (derived from the Brent and Providence corpus, respectively) for a set of 600 target words (from the wordbank project.

Code

The three jupyter notebooks contain python code for prosody feature analysis (egemap_prosody_feature_analysis.ipnb); language model-derived feature analysis (srilm_features_analysis.ipnb); and ridge regression models for predicting the age of acquisition of words using egemap prosody (experiment 1 in the paper) features and language model-derived features (experiment 3 in the paper) (python_regression.ipnb).

Citation

@article{frermann:frank:2017,
  author = {Lea Frermann and Michael C. Frank},
  title = {Prosodic Features from Large Corpora of Child-Directed Speech as Predictors of the Age of Acquisition of Words},
  year={2017},
  journal = "arXiv preprint cs.CL/1709.09443"
}