arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.09978cs.CLcs.AIcs.LG
收藏

NLP机器学习模型的鲁棒性测试:搜索和语义替换

Robustness Tests of NLP Machine Learning Models: Search and Semantically Replace

Wells Fargo(富国银行)

Rahul Singh, Karan Jindal, Yufei Yu, Hanyu Yang, Tarun Joshi, Matthew A. Campbell, Wayne B. Shoumaker

摘要:

本文提出了一种策略来评估涉及自然语言处理(NLP)的不同机器学习模型的鲁棒性。整个方法依赖于搜索和语义替换策略,该策略包括两个步骤:(1)搜索,识别文本中的重要部分;(2)语义替换,找到重要部分的替换,并使用语义相似的单词约束替换的标记。我们介绍了专门为特定类型的机器学习模型设计的不同类型的搜索和语义替换方法。我们还研究了这种策略的有效性,并提供了一个通用的框架来评估各种机器学习模型。最后,提供了一个实证比较的鲁棒性性能之间的三种不同的模型类型,每一个不同的文本表示。

英文摘要:

This paper proposes a strategy to assess the robustness of different machine learning models that involve natural language processing (NLP). The overall approach relies upon a Search and Semantically Replace strategy that consists of two steps: (1) Search, which identifies important parts in the text; (2) Semantically Replace, which finds replacements for the important parts, and constrains the replaced tokens with semantically similar words. We introduce different types of Search and Semantically Replace methods designed specifically for particular types of machine learning models. We also investigate the effectiveness of this strategy and provide a general framework to assess a variety of machine learning models. Finally, an empirical comparison is provided of robustness performance among three different model types, each with a different text representation.

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。

↑