Recurrent Neural Network Language Models Always Learn English-Like Relative Clause Attachment

This repository contains the raw results (by word information-theoretic measures for the experimental stimuli) and the LSTM models analyzed in Recurrent Neural Network Language Models Always Learn English-Like Relative Clause Attachment. The models from the synthetic experiments are given in the synthetic archive, as well as the training data generation script. There is a README included that gives more details for recreating/evaluating results from those experiments.

The naming convention for each model in the models directory is:
[Language]_hidden[Hidden Units]_batch[Batch Size]_dropout[Dropout Rate]_lr[Learning Rate]_[Model Number].pt

Language: en for English and es for Spanish
Hidden Units: All models had two layers with 650 hidden units per layer
Batch Size: The size of the batch (128 for English, 64 for Spanish)
Dropout Rate: All models used a dropout rate of 0.2
Learning Rate: All models has a learning rate of 20
Model Number: Identifier of the model (English model 0 is the best model from Gulordava et al. (2018))