Question Answering Using Match-LSTM and Answer Pointer

Machine comprehension of text is a significant problem in natural language processing today – in this project, we tackle machine reading comprehension as applied to question answering. Our goal is: given a question and a context paragraph, to extract from the paragraph the answer to the question. As an oracle, on the dataset we used, humans score over 86.8% accuracy (EM) on the test set for this task, while the best models only achieve roughly 75%. Existing approaches to this extractive Question Answering problem typically involve an encoding layer that encodes the question and paragraph into a sequence, some additional layer that accounts for interaction between the question and paragraph, and a final decoding layer that extracts the answer from the paragraph [2][3][4][7]. In this paper, we will follow a similar structure, using LSTMs in our encoding and decoding layers, and calculating attention as our interaction layer.