构建代码混合通用依存森林以实现无偏跨语言关系抽取
Constructing Code-mixed Universal Dependency Forest for Unbiased Cross-lingual Relation Extraction
AI总结：
针对跨语言关系抽取中UD结构迁移存在源语或目标语偏置的问题，本文提出融合源端与目标端UD树的代码混合UD森林，并在ACE基准上验证其可显著提升性能。
摘要：
近期跨语言关系抽取（XRE）研究大量利用通用依存（UD）资源中语言一致的结构特征，但由于语言之间不可避免的语言差异，这些方法可能严重受到有偏迁移（例如目标语偏置或源语偏置）的影响。本文通过构建一种代码混合UD森林，研究基于UD的无偏XRE迁移。我们首先将源语言句子翻译成并行的目标语言句子，并分别为二者解析UD树。随后，将源端和目标端的UD结构合并为统一的代码混合UD森林。借助此类森林特征，可有效弥合基于UD的XRE在训练阶段与预测阶段之间的差距。我们在ACE XRE基准数据集上进行实验，结果表明，所提出的代码混合UD森林有助于实现基于UD的无偏XRE迁移，并借此取得显著的XRE性能提升。
英文摘要：
Latest efforts on cross-lingual relation extraction (XRE) aggressively leverage the language-consistent structural features from the universal dependency (UD) resource, while they may largely suffer from biased transfer (e.g., either target-biased or source-biased) due to the inevitable linguistic disparity between languages. In this work, we investigate an unbiased UD-based XRE transfer by constructing a type of code-mixed UD forest. We first translate the sentence of the source language to the parallel target-side language, for both of which we parse the UD tree respectively. Then, we merge the source-/target-side UD structures as a unified code-mixed UD forest. With such forest features, the gaps of UD-based XRE between the training and predicting phases can be effectively closed. We conduct experiments on the ACE XRE benchmark datasets, where the results demonstrate that the proposed code-mixed UD forests help unbiased UD-based XRE transfer, with which we achieve significant XRE performance gains.
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。
