教机器编码：具有视觉注意力的神经标记生成
Teaching Machines to Code: Neural Markup Generation with Visual Attention
摘要：
我们提出了一个具有视觉注意力的神经传感器模型，该模型学习生成现实世界数学公式的LaTeX标记。应用序列建模和转导技术，已经非常成功的方式，如自然语言，图像，手写，语音和音频;我们构建了一个图像到标记模型，学习产生语法和语义正确的LaTeX标记代码超过150个单词长，并实现了89%的BLEU分数;改进了以前的最先进的Im 2Latex问题。我们还通过热图可视化演示了注意力如何帮助解释模型，并且尽管在没有任何限界框数据的情况下进行了训练，但仍然可以准确地定位（检测和定位）图像上的符号。
英文摘要：
We present a neural transducer model with visual attention that learns to generate LaTeX markup of a real-world math formula given its image. Applying sequence modeling and transduction techniques that have been very successful across modalities such as natural language, image, handwriting, speech and audio; we construct an image-to-markup model that learns to produce syntactically and semantically correct LaTeX markup code over 150 words long and achieves a BLEU score of 89%; improving upon the previous state-of-art for the Im2Latex problem. We also demonstrate with heat-map visualization how attention helps in interpreting the model and can pinpoint (detect and localize) symbols on the image accurately despite having been trained without any bounding box data.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
