Incorporating Priors with Feature Attribution on Text Classification
Incorporating Priors with Feature Attribution on Text Classification
复制标题
将先验与文本分类的特征归因相结合
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Besim Avci
中科院分区：
文献类型：
--
作者：
Frederick Liu;Besim Avci
最近提出的特征归因方法可以帮助用户解释复杂模型的预测。我们的方法将特征属性集成到目标函数中，以允许机器学习从业者将先验知识纳入模型构建中。为了证明我们的技术的有效性，我们将其应用于两个任务：（1）通过中和身份术语来减轻文本分类器中的意外偏见;（2）通过迫使模型专注于有毒术语来提高分类器在稀缺数据设置中的性能。我们的方法增加了一个L2之间的距离损失的功能属性和任务特定的先验值的目标。我们的实验表明，i）用我们的技术训练的分类器减少了不期望的模型偏差，而没有对原始任务进行权衡; ii）在稀缺数据设置中结合先验帮助模型性能。
Feature attribution methods, proposed recently, help users interpret the predictions of complex models. Our approach integrates feature attributions into the objective function to allow machine learning practitioners to incorporate priors in model building. To demonstrate the effectiveness our technique, we apply it to two tasks: (1) mitigating unintended bias in text classifiers by neutralizing identity terms; (2) improving classifier performance in scarce data setting by forcing model to focus on toxic terms. Our approach adds an L2 distance loss between feature attributions and task-specific prior values to the objective. Our experiments show that i) a classifier trained with our technique reduces undesired model biases without a tradeoff on the original task; ii) incorporating prior helps model performance in scarce data settings.