Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation
Emily Dinan∗, Angela Fan †, Adina Williams, Jack Urbanek, Douwe Kiela, Jason Weston Facebook AI Research †Laboratoire Lorrain d'Informatique et Applications (LORIA) Joint first authors.
Abstract
Models often easily learn biases present in the training data, and their predictions directly reflect this bias. We analyze gender bias in dialogue data, and examine how this bias is actually amplified in subsequent generative chit-chat dialogue models. We measure gender bias in six existing dialogue datasets, and focus on the most biased one, the multi-player text-based fantasy adventure dataset LIGHT Urbanek et al. (2019), as a testbed for our bias mitigation techniques. The LIGHT dataset is highly imbalanced with respect to gender, containing predominantly male characters, likely because it is entirely collected by crowdworkers and reflects common biases that exist in fantasy or medieval settings. We consider three techniques to mitigate gender bias: counterfactual data augmentation, targeted data collection, and bias controlled training. We show that our proposed techniques mitigate gender bias in LIGHT by balancing the genderedness of generated dialogue utterances and are particularly effective in combination. We quantify performance using various evaluation methods—such as quantity of gendered words, a dialogue safety classifier, and human studies—all of which show that our m
中文速览
对话系统中的性别偏见问题长期被忽视——模型会直接学习并放大训练数据里的偏见，比如把"妻子"角色和做饭打扫强行绑定。研究者系统测量了六个主流对话数据集的性别偏见程度，发现奇幻冒险对话数据集LIGHT最为严重（73%的性别词汇指向男性），于是以它为测试平台，提出三种去偏方法：反事实数据增强（Counterfactual Data Augmentation，自动对调性别词汇）、正向数据收集（人工补充更多女性角色及对话）、以及偏见可控生成（训练时给模型加入性别控制信号）。实验结果显示，三种方法联合使用效果最佳，模型生成的回复中性别词汇分布更加均衡、冒犯性内容明显减少，同时人工评估和自动评估均证实对话的吸引力并未下降。这项工作为对话系统的公平性提供了一套可落地的去偏框架，对任何面向真实用户的聊天助手都具有直接的参考价值。
原文 arXiv:1911.03842;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1911.03842v2