Question Answering Experiments

Training Details

For pre-training MemN2N and QACNN on MovieQA, we followed the exact procedure as in Tapaswi et al. (2016) and Liu et al. (2017), respectively. Each model was trained on training set of the MovieQA task and tuned on the dev set, and the best performaning models on the dev set were later fine-tuned on the target dataset During fine-tuning, the model was also trained on the training set of target datasets and tune on the dev set, and the performance on the testing set of the target datasets was reported as the final result. We use accuracy as the performance measurement.

Figure1. Overall Flow of Transfer Learning