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 1804.08166cs.CL
收藏

基于词嵌入扰动的句子分类

Word Embedding Perturbation for Sentence Classification

CS 682, UMass Amherst(马萨诸塞大学阿默斯特分校)

Dongxu Zhang, Zhichao Yang

摘要:

在这份技术报告中,我们的目标是通过应用数据增强方法来缓解自然语言的过拟合问题。具体地说,我们尝试了几种类型的噪声干扰输入词嵌入,如高斯噪声,伯努利噪声,对抗噪声等,我们也适用于不同类型的噪声的几个限制。通过实施这些提出的数据增强方法,基线模型可以在几个句子分类任务上获得改进。

英文摘要:

In this technique report, we aim to mitigate the overfitting problem of natural language by applying data augmentation methods. Specifically, we attempt several types of noise to perturb the input word embedding, such as Gaussian noise, Bernoulli noise, and adversarial noise, etc. We also apply several constraints on different types of noise. By implementing these proposed data augmentation methods, the baseline models can gain improvements on several sentence classification tasks.

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。

↑