Understanding the Origins of Bias in Word Embeddings
Understanding the Origins of Bias in Word Embeddings
复制标题
了解词嵌入中偏差的起源
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
R. Zemel
中科院分区：
文献类型：
--
作者：
Marc;Colleen Alkalay;Ashton Anderson;R. Zemel
机器学习系统的力量不仅带来了巨大的技术进步，但也面临着社会危害的风险。作为最近的一个例子，研究人员表明，流行的词嵌入算法表现出刻板印象的偏见，例如性别偏见。这些算法在机器学习系统中的广泛使用，从自动翻译服务到简历扫描仪，可以放大重要环境中的刻板印象。尽管已经开发出方法来测量这些偏差并改变词嵌入以减轻其偏差表示，但人们对词嵌入偏差如何依赖于训练数据缺乏了解。在这项工作中，我们开发了一种技术来理解词嵌入中偏差的起源。给定在语料库上训练的词嵌入，我们的方法可以识别语料库的扰动将如何影响最终嵌入的偏差。这可用于将词嵌入偏差的起源追溯到原始训练文档。使用我们的方法，人们可以调查基础语料库偏差的趋势，并确定删除哪些文档子集最能减少偏差。我们在《纽约时报》和维基百科语料库上展示了我们的技术，发现我们基于影响函数的近似非常准确。
The power of machine learning systems not only promises great technical progress, but risks societal harm. As a recent example, researchers have shown that popular word embedding algorithms exhibit stereotypical biases, such as gender bias. The widespread use of these algorithms in machine learning systems, from automated translation services to curriculum vitae scanners, can amplify stereotypes in important contexts. Although methods have been developed to measure these biases and alter word embeddings to mitigate their biased representations, there is a lack of understanding in how word embedding bias depends on the training data. In this work, we develop a technique for understanding the origins of bias in word embeddings. Given a word embedding trained on a corpus, our method identifies how perturbing the corpus will affect the bias of the resulting embedding. This can be used to trace the origins of word embedding bias back to the original training documents. Using our method, one can investigate trends in the bias of the underlying corpus and identify subsets of documents whose removal would most reduce bias. We demonstrate our techniques on both a New York Times and Wikipedia corpus and find that our influence function-based approximations are very accurate.
影响因子：
7.6
作者：
Greenwald, AG;McGhee, DE;Schwartz, JLK
通讯作者：
Schwartz, JLK
DOI：
10.18653/v1/n18-2003
发表时间：
2018-04
期刊：
ArXiv
影响因子：
--
作者：
Jieyu Zhao;Tianlu Wang;Mark Yatskar;Vicente Ordonez;Kai-Wei Chang
通讯作者：
Jieyu Zhao;Tianlu Wang;Mark Yatskar;Vicente Ordonez;Kai-Wei Chang