arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1704.04441cs.CL
收藏

标签和MT中基于字符串的词嵌入对Wrod Scramlbing或Randdm Nouse的鲁棒性如何?

How Robust Are Character-Based Word Embeddings in Tagging and MT Against Wrod Scramlbing or Randdm Nouse?

DFKI(德国人工智能研究中心);Saarland University(萨尔大学)

Georg Heigold, Günter Neumann, Josef van Genabith

摘要:

本文研究了NLP对扰动词形式的鲁棒性。虽然神经方法可以在某些任务和条件下实现(几乎)类似人类的准确性,但它们通常对输入中的小变化敏感,例如非规范输入(例如,错别字)。然而,在涉及用户生成内容的应用中,稳定性和鲁棒性都是所需的属性,并且随着人类容易应对这种嘈杂或敌对条件,稳定性和鲁棒性更是如此。在本文中,我们研究了噪声输入的影响。我们考虑不同的噪声分布(一种类型的噪声,噪声类型的组合)和不匹配的噪声分布进行训练和测试。此外,我们经验性地评估了不同模型(卷积神经网络、递归神经网络、非神经模型)、不同基本单元(字符、字节对编码单元)和不同NLP任务(形态标记、机器翻译)的鲁棒性。

英文摘要:

This paper investigates the robustness of NLP against perturbed word forms. While neural approaches can achieve (almost) human-like accuracy for certain tasks and conditions, they often are sensitive to small changes in the input such as non-canonical input (e.g., typos). Yet both stability and robustness are desired properties in applications involving user-generated content, and the more as humans easily cope with such noisy or adversary conditions. In this paper, we study the impact of noisy input. We consider different noise distributions (one type of noise, combination of noise types) and mismatched noise distributions for training and testing. Moreover, we empirically evaluate the robustness of different models (convolutional neural networks, recurrent neural networks, non-neural models), different basic units (characters, byte pair encoding units), and different NLP tasks (morphological tagging, machine translation).

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。

↑