arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1609.07568cs.CL
收藏

一种用于相似语言和方言区分的多级卷积神经网络

A Character-level Convolutional Neural Network for Distinguishing Similar Languages and Dialects

MIT Computer Science and Artificial Intelligence Laboratory(麻省理工学院计算机科学与人工智能实验室)

Yonatan Belinkov, James Glass

摘要:

区分密切相关的语言变体被认为是一项具有挑战性和重要的任务。本文描述了我们提交的DSL 2016共享任务,其中包括两个子任务:一个是区分相似的语言,一个是识别阿拉伯语方言。我们为此开发了一个字符级的神经网络。给定一个字符序列,我们的模型将每个字符嵌入到向量空间中,通过具有不同过滤器宽度的多个卷积来运行序列,并将卷积表示池化以获得用于预测语言或方言的文本的隐藏向量表示。我们主要专注于阿拉伯语方言识别任务,获得了0.4834的F1分数,在18名参与者中排名第6。我们还详细分析了我们的系统在阿拉伯数据上所犯的错误,并指出了这种方法所面临的挑战。

英文摘要:

Discriminating between closely-related language varieties is considered a challenging and important task. This paper describes our submission to the DSL 2016 shared-task, which included two sub-tasks: one on discriminating similar languages and one on identifying Arabic dialects. We developed a character-level neural network for this task. Given a sequence of characters, our model embeds each character in vector space, runs the sequence through multiple convolutions with different filter widths, and pools the convolutional representations to obtain a hidden vector representation of the text that is used for predicting the language or dialect. We primarily focused on the Arabic dialect identification task and obtained an F1 score of 0.4834, ranking 6th out of 18 participants. We also analyze errors made by our system on the Arabic data in some detail, and point to challenges such an approach is faced with.

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。

↑