Hierarchical Attention Fusion Network for Question Answering

[1] Seo, M., Kembhavi, A., Farhadi, A., etc. (2016). Bidirectional attention flow for machine comprehension. arXiv preprint arXiv:1611.01603. [2] Kim, Y., Jernite, Y., Sontag, D., etc. (2016). Character-aware neural language models. In 13th AAAI Conference on Artificial Intelligence. [3] Wang, W., Yan, M., Wu, C. (2018). Multi-Granularity Hierarchical Attention Fusion Networks for Reading Comprehension and Question Answering. arXiv preprint arXiv:1811.11934. ● Goal: Build a Question Answering model on Stanford Question Answering Dataset (SQuAD) ● Data: Default SQuAD train, dev, test set provided by TA ● Evaluation: F1, EM