论文标题
探测基于变压器的语言模型中的多语言数值理解
Probing for Multilingual Numerical Understanding in Transformer-Based Language Models
论文作者
论文摘要
自然语言数字是组成结构的一个例子，其中较大的数字由较小数字的操作组成。鉴于构图推理是自然语言理解的关键，我们提出了在Distilbert，XLM和BERT上测试的新型多语言探测任务，以调查各种自然语言数量系统中数值数据的组成推理证据。通过使用英语，日语，丹麦和法语的语法判断和价值比较分类任务，我们发现证据表明这些预算模型中编码的信息足以进行语法判断，但通常不进行价值比较。我们分析了这一可能的原因，并讨论如何在进一步的研究中扩展我们的任务。
Natural language numbers are an example of compositional structures, where larger numbers are composed of operations on smaller numbers. Given that compositional reasoning is a key to natural language understanding, we propose novel multilingual probing tasks tested on DistilBERT, XLM, and BERT to investigate for evidence of compositional reasoning over numerical data in various natural language number systems. By using both grammaticality judgment and value comparison classification tasks in English, Japanese, Danish, and French, we find evidence that the information encoded in these pretrained models' embeddings is sufficient for grammaticality judgments but generally not for value comparisons. We analyze possible reasons for this and discuss how our tasks could be extended in further studies.
