通过多语言主谓一致探索句嵌入中的句法信息
Exploring syntactic information in sentence embeddings through multilingual subject-verb agreement
AI总结：
本文通过新的多项选择任务和Blackbird Language Matrices数据集，采用两级架构研究多语言预训练语言模型的句法表征，发现其存在语言特异性差异，句法结构在密切相关语言间也不共享。
摘要：
本文旨在研究多语言预训练语言模型在多大程度上捕捉跨语言有效的抽象语言表征。我们的方法是大规模开发具有特定属性的精选合成数据，并利用这些数据研究基于预训练语言模型构建的句表征。我们使用一项新的多项选择任务和数据集Blackbird Language Matrices（BLMs，黑鸟语言矩阵），聚焦于多种语言中特定的语法结构现象——不同句子结构中的主谓一致。解决该任务需要系统检测文本表征中的复杂语言模式和范式。通过采用分两步解决问题的两级架构（检测单个句子中的句法对象及其属性，以及在输入句子序列中寻找模式），我们发现，尽管多语言预训练语言模型在多语言文本上以一致方式训练，但它们存在语言特异性差异，句法结构甚至在密切相关的语言间也不共享。
英文摘要：
In this paper, our goal is to investigate to what degree multilingual pretrained language models capture cross-linguistically valid abstract linguistic representations. We take the approach of developing curated synthetic data on a large scale, with specific properties, and using them to study sentence representations built using pretrained language models. We use a new multiple-choice task and datasets, Blackbird Language Matrices (BLMs), to focus on a specific grammatical structural phenomenon -- subject-verb agreement across a variety of sentence structures -- in several languages. Finding a solution to this task requires a system detecting complex linguistic patterns and paradigms in text representations. Using a two-level architecture that solves the problem in two steps -- detect syntactic objects and their properties in individual sentences, and find patterns across an input sequence of sentences -- we show that despite having been trained on multilingual texts in a consistent manner, multilingual pretrained language models have language-specific differences, and syntactic structure is not shared, even across closely related languages.
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。
