论文标题
说话者信息可以指导模型以更好的归纳偏见：有关预测代码转换的案例研究
Speaker Information Can Guide Models to Better Inductive Biases: A Case Study On Predicting Code-Switching
论文作者
论文摘要
自然语言处理（NLP）模型接受了人们生成的数据的培训可能是不可靠的，因为如果没有任何约束，他们就可以从与任务无关的虚假相关性中学习。我们假设以受控的，受过良好教育的方式通过扬声器信息丰富模型可以指导他们挑选相关的归纳偏见。对于在英语双语对话中预测代码转换点的扬声器驱动的任务，我们表明，作为预期提示，添加社会语言的扬声器功能可显着提高准确性。我们发现，通过在输入中添加有影响力的短语，说话者信息的模型学习有用且可解释的语言信息。据我们所知，我们是第一个将说话者特征纳入用于代码开关的神经模型中的人，更普遍地，迈出了以受控方式使用扬声器信息的透明，个性化模型迈出的一步。
Natural language processing (NLP) models trained on people-generated data can be unreliable because, without any constraints, they can learn from spurious correlations that are not relevant to the task. We hypothesize that enriching models with speaker information in a controlled, educated way can guide them to pick up on relevant inductive biases. For the speaker-driven task of predicting code-switching points in English--Spanish bilingual dialogues, we show that adding sociolinguistically-grounded speaker features as prepended prompts significantly improves accuracy. We find that by adding influential phrases to the input, speaker-informed models learn useful and explainable linguistic information. To our knowledge, we are the first to incorporate speaker characteristics in a neural model for code-switching, and more generally, take a step towards developing transparent, personalized models that use speaker information in a controlled way.
