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.
Natural Language Inference over Interaction Space: ICLR 2018 Reproducibility Report
An attempt to reproduce the results of the paper "Natural Language Inference over Interaction Space" yielded 86.38% accuracy on the Stanford NLI dataset, compared to the claimed 88.0%, with differences noted in optimizers and model selection.
- Year
- 2018
- Venue
- arXiv 2018
- Authors
- 3
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/1802.03198ARXIV-DEFAULT
- TL;DR
- Semantic Scholar