We present 3 different question-answering models trained on the SQuAD2.0 dataset -- BIDAF, DocumentQA and ALBERT Retro-Reader -- demonstrating the improvement of language models in the past three years. Through our research in fine-tuning pre-trained models for question-answering, we developed a novel approach capable of achieving a 2% point improvement in SQuAD2.0 F1 in reduced training time. Our method of re-initializing select layers of a parameter-shared language model is simple yet empirically powerful.
@article{arxiv.2105.00328,
title = {When to Fold'em: How to answer Unanswerable questions},
author = {Marshall Ho and Zhipeng Zhou and Judith He},
journal= {arXiv preprint arXiv:2105.00328},
year = {2021}
}