arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1507.01053cs.NEcs.CLcs.CVcs.LG
收藏

使用基于注意的编码器-解码器网络描述多媒体内容

Describing Multimedia Content using Attention-based Encoder--Decoder Networks

Université de Montréal(蒙特利尔大学)

Kyunghyun Cho, Aaron Courville, Yoshua Bengio

摘要:

虽然深度神经网络最初主要用于分类任务,但它们正在结构化输出问题领域中迅速扩展,其中观察到的目标由多个随机变量组成,这些变量具有丰富的联合分布,给定输入。我们在本文中的重点是输入也有一个丰富的结构和输入和输出的结构是某种程度上相关的情况下。我们描述的系统,学习参加不同的地方在输入,为每个元素的输出,为各种任务:机器翻译,图像字幕生成,视频剪辑描述和语音识别。所有这些系统都基于一组共享的构建模块:门控递归神经网络和卷积神经网络,以及经过训练的注意力机制。我们报告这些系统的实验结果,表现出令人印象深刻的良好性能和优势的注意力机制。

英文摘要:

Whereas deep neural networks were first mostly used for classification tasks, they are rapidly expanding in the realm of structured output problems, where the observed target is composed of multiple random variables that have a rich joint distribution, given the input. We focus in this paper on the case where the input also has a rich structure and the input and output structures are somehow related. We describe systems that learn to attend to different places in the input, for each element of the output, for a variety of tasks: machine translation, image caption generation, video clip description and speech recognition. All these systems are based on a shared set of building blocks: gated recurrent neural networks and convolutional neural networks, along with trained attention mechanisms. We report on experimental results with these systems, showing impressively good performance and the advantage of the attention mechanism.

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。

↑