We develop the first approximate inference algorithm for 1-Best (and M-Best) decoding in bidirectional neural sequence models by extending Beam Search (BS) to reason about both forward and backward time dependencies. Beam Search (BS) is a widely used approximate inference algorithm for decoding sequences from unidirectional neural sequence models. Interestingly, approximate inference in bidirectional models remains an open problem, despite their significant advantage in modeling information from both the past and future. To enable the use of bidirectional models, we present Bidirectional Beam Search (BiBS), an efficient algorithm for approximate bidirectional inference.To evaluate our method and as an interesting problem in its own right, we introduce a novel Fill-in-the-Blank Image Captioning task which requires reasoning about both past and future sentence structure to reconstruct sensible image descriptions. We use this task as well as the Visual Madlibs dataset to demonstrate the effectiveness of our approach, consistently outperforming all baseline methods.

开发Bidirectional Beam Search（BiBS）算法来逼近推理双向神经序列模型中的1-Best（和M-Best）解码，并在可视化任务中验证该方法的高效性和效果。

双向束搜索：神经序列模型的前向-后向推理用于填空图像字幕生成