利用深度学习对托福听力部分进行机器理解

Machine Comprehension for the TOEFL Listening by Using Deep Learning Technology

用户浏览文本比较方便,但由于音频内容不能直接显示在屏幕上,因此,访问大量音频内容比访问文本内容更困难、更耗时。所以,开发能够理解音频内容的机器是很有帮助的。文中提出了一个新的方法来机器理解口语内容。通过利用自然语言的层次结构和注意力的选择能力机制来对托福听力测试内容进行机器理解。实验结果表明,这个方法相比于其他方法有较高准确度。

The user can easily browse the text,but the audio content cannot be directly displayed on the screen.Therefore,accessing large amounts of audio contents is more difficult and time-consuming than accessing text contents.Therefore,it is helpful to develop a machine that can understand audio content.In this article,a new method is proposed to understand spoken content by machine.We use the natural language hierarchy and attention selection mechanism to machine comprehend the content of the TOEFL listening test.Experimental results show that this method has higher accuracy than other methods.