Human biases are ubiquitous but not uniform: disparities exist across
linguistic, cultural, and societal borders. As large amounts of recent
literature suggest, language models (LMs) trained on human data can reflect and
often amplify the effects of these social biases. However, the vast majority of
existing studies on bias are heavily skewed towards Western and European
languages. In this work, we scale the Word Embedding Association Test (WEAT) to
24 languages, enabling broader studies and yielding interesting findings about
LM bias. We additionally enhance this data with culturally relevant information
for each language, capturing local contexts on a global scale. Further, to
encompass more widely prevalent societal biases, we examine new bias dimensions
across toxicity, ableism, and more. Moreover, we delve deeper into the Indian
linguistic landscape, conducting a comprehensive regional bias analysis across
six prevalent Indian languages. Finally, we highlight the significance of these
social biases and the new dimensions through an extensive comparison of
embedding methods, reinforcing the need to address them in pursuit of more
equitable language models. All code, data and results are available here:
this https URL

这项研究通过对 24 种语言进行 Word Embedding Association Test (WEAT) 的扩展，以更广阔的研究视角揭示了语言模型的偏见，并通过在全球范围内捕捉有关每种语言的文化相关信息，进一步提高了数据的质量。文章还展示了对毒性、庸能主义等方面的新偏见维度的研究，并通过对印度六种常用语言进行了全面的地区偏见分析，最后通过对嵌入方法的广泛比较强调了这些社会偏见和新维度的重要性，同时强调了解决这些问题对建立更公平的语言模型的必要性。

全球之音、地方偏见：跨语言的社会文化偏见

Global Voices, Local Biases: Socio-Cultural Prejudices across Languages

The Word Embedding Association Test shows that GloVe and word2vec word
embeddings exhibit human-like implicit biases based on gender, race, and other
social constructs (Caliskan et al., 2017). Meanwhile, research on learning
reusable text representations has begun to explore sentence-level texts, with
some sentence encoders seeing enthusiastic adoption. Accordingly, we extend the
Word Embedding Association Test to measure bias in sentence encoders. We then
test several sentence encoders, including state-of-the-art methods such as ELMo
and BERT, for the social biases studied in prior work and two important biases
that are difficult or impossible to test at the word level. We observe mixed
results including suspicious patterns of sensitivity that suggest the test's
assumptions may not hold in general. We conclude by proposing directions for
future work on measuring bias in sentence encoders.

本研究在 Word Embedding Association Test 的基础上，对句子编码进行了偏差测量，实验包括了包括 ELMo 和 BERT 在内的多种方法，并提议了未来的研究方向。