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 2506.02447cs.HC
收藏

用于交互式调整词嵌入去偏效果的可视化方法

Visualization for interactively adjusting the de-bias effect of word embedding

Arisa Sugino, Takayuki Itoh

AI总结:

本文针对日语词嵌入中的性别偏见问题,提出一种交互式可视化方法,可按词类别调整去偏程度,并通过优化方案在去偏与保持模型性能之间提供多种配置选择。

摘要:

词嵌入将词语转换为数值,是一种重要的自然语言处理技术并被广泛使用。词嵌入的一个严重问题是,如果用于预训练的数据集包含偏见,模型就会学习到这种偏见并受到影响。另一方面,即使偏见对我们来说是不受欢迎的,不加区分地从词嵌入中去除偏见也可能导致信息丢失。因此,去偏导致模型性能下降的风险将成为另一个问题。作为该问题的解决方案,我们聚焦于日语中的性别偏见,提出了一种交互式可视化方法,用于针对每个词类别调整去偏的程度。具体来说,我们可视化了去偏后在类别分类任务中的准确率,并允许用户基于可视化结果调整参数,从而使去偏能够根据用户的目标进行调整。此外,考虑到去偏与防止模型性能下降之间的权衡,以及不同人对性别偏见的感知不同,我们开发了一种机制,通过应用优化方案来呈现多种去偏配置选择。本文展示了一项实验结果,在该实验中,我们移除了从日语版维基百科学习到的词嵌入中的性别偏见。我们基于新闻语料库将词语分为五个类别,并观察到去偏的影响程度在不同类别之间差异很大。随后,我们根据可视化结果对每个类别的去偏程度进行了调整。

英文摘要:

Word embedding, which converts words into numerical values, is an important natural language processing technique and widely used. One of the serious problems of word embedding is that the bias will be learned and affect the model if the dataset used for pre-training contains bias. On the other hand, indiscriminate removal of bias from word embeddings may result in the loss of information, even if the bias is undesirable to us. As a result, a risk of model performance degradation due to bias removal will be another problem. As a solution to this problem, we focus on gender bias in Japanese and propose an interactive visualization method to adjust the degree of debias for each word category. Specifically, we visualize the accuracy in a category classification task after debiasing, and allow the user to adjust the parameters based on the visualization results, so that the debiasing can be adjusted according to the user's objectives. In addition, considering a trade-off between debiasing and preventing degradation of model performance, and that different people perceive gender bias differently, we developed a mechanism to present multiple choices of debiasing configurations applying an optimization scheme. This paper presents the results of an experiment in which we removed the gender bias for word embeddings learned from the Japanese version of Wikipedia. We classified words into five categories based on a news corpus, and observed that the degree of influence of debiasing differed greatly among the categories. We then adjusted the degree of debiasing for each category based on the visualization results.

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。

↑