Joint vision and language tasks like visual question answering are
fascinating because they explore high-level understanding, but at the same
time, can be more prone to language biases. In this paper, we explore the
biases in the MovieQA dataset and propose a strikingly simple model which can
exploit them. We find that using the right word embedding is of utmost
importance. By using an appropriately trained word embedding, about half the
Question-Answers (QAs) can be answered by looking at the questions and answers
alone, completely ignoring narrative context from video clips, subtitles, and
movie scripts. Compared to the best published papers on the leaderboard, our
simple question + answer only model improves accuracy by 5% for video +
subtitle category, 5% for subtitle, 15% for DVS and 6% higher for scripts.

本研究探讨电影问答数据集中存在的语言偏见，提出一个简单的模型，通过合适的词向量训练，能够在不考虑视频和字幕等故事情境的情况下，通过观察问题和答案来回答约一半的问题。与排行榜上发表的最佳论文相比，我们的简单问题 + 答案模型在视频 + 字幕类别精度提高了 5％，在字幕、DVS 和剧本方面精度更是提高了 15％，这表明使用适当的词向量训练能够大大提高问答准确度。

电影问答：我们是否在问正确的问题？

Are we asking the right questions in MovieQA?

In this paper, we introduce Query-based Attention CNN(QACNN) for Text
Similarity Map, an end-to-end neural network for question answering. This
network is composed of compare mechanism, two-staged CNN architecture with
attention mechanism, and a prediction layer. First, the compare mechanism
compares between the given passage, query, and multiple answer choices to build
similarity maps. Then, the two-staged CNN architecture extracts features
through word-level and sentence-level. At the same time, attention mechanism
helps CNN focus more on the important part of the passage based on the query
information. Finally, the prediction layer find out the most possible answer
choice. We conduct this model on the MovieQA dataset using Plot Synopses only,
and achieve 79.99% accuracy which is the state of the art on the dataset.

介绍了一种用于问答的端到端神经网络，名为 Query-based Attention CNN (QACNN)，并在基于电影情节的数据集（MovieQA dataset）上实现 79.99% 的准确率，成为该数据集的最佳模型。