- This paper demonstrates a methodology for obtaining a large number of document-query-answer triples
- The results show that the Attentive and Impatient Readers are able to propagate and integrate semantic information over long distances
- The key contributor is the incorporation of an attention mechanism
- Using the techniques in this paper, significantly bigger training data sets can be used to train more expressive and accurate models

Teaching Machines to Read and Comprehend Conclusion

Ohio State University, Columbus

- The researchers predict the neural models should in principle be well suited for this task
- The researchers predict the simple recurrent models such as the LSTM probably have insufficient expressive power for solving tasks that require complex inference
- The researchers predict the attention-based models would therefore outperform the pure LSTM-based approaches

Teaching Machines to Read and Comprehend Hypothesis

Hermann, K. M., Kocisky, T., Grefenstette, E., Espeholt, L., Kay, W., Suleyman, M., & Blunsom, P. (2015). Teaching machines to read and comprehend. Advances in neural information processing systems, 28, 1693-1701.
https://arxiv.org/abs/1506.03340v3

Learn Before

Learn After

Learn After