Natural Language Inference over Interaction Space: ICLR 2018 Reproducibility Report
This is an incremental reproducibility study for the NLP community, focusing on verifying results in natural language inference.
The researchers attempted to reproduce the results of the 'Natural Language Inference over Interaction Space' paper from ICLR 2018, achieving 86.38% accuracy on the Stanford NLI test set compared to the claimed 88.0% accuracy, with differences attributed to optimizers and model selection methods.
We have tried to reproduce the results of the paper "Natural Language Inference over Interaction Space" submitted to ICLR 2018 conference as part of the ICLR 2018 Reproducibility Challenge. Initially, we were not aware that the code was available, so we started to implement the network from scratch. We have evaluated our version of the model on Stanford NLI dataset and reached 86.38% accuracy on the test set, while the paper claims 88.0% accuracy. The main difference, as we understand it, comes from the optimizers and the way model selection is performed.