Machine Comprehension Based on Learning to Rank
This work addresses the challenge of training cost for researchers and practitioners in NLP, but it is incremental as it builds on existing datasets and methods.
The paper tackled the problem of expensive training in machine comprehension by proposing a feature-engineered approach with semantics on a large-scale news article dataset, achieving good performance with efficiency and less training data.
Machine comprehension plays an essential role in NLP and has been widely explored with dataset like MCTest. However, this dataset is too simple and too small for learning true reasoning abilities. \cite{hermann2015teaching} therefore release a large scale news article dataset and propose a deep LSTM reader system for machine comprehension. However, the training process is expensive. We therefore try feature-engineered approach with semantics on the new dataset to see how traditional machine learning technique and semantics can help with machine comprehension. Meanwhile, our proposed L2R reader system achieves good performance with efficiency and less training data.