Figure 1: QACNN architecture overview. The trainable parameters, including $E$, $W_{CNN}^{(1)}$, $W_{CNN}^{(2)}$, $W_{FC}^{(1)}$, and $W_{FC}^{(2)}$, are colored in light blue.

Figure 4: Visualization of the changes of the word-level attention map in the first stage CNN of QACNN in different training epochs. The more red, the more the QACNN views the word as a key feature. The input story-question-choices triplet is the same as the one in Table 1.