Constructing Code-mixed Universal Dependency Forest for Unbiased Cross-lingual Relation Extraction

TL;DR

This paper introduces a novel method for cross-lingual relation extraction that constructs code-mixed universal dependency forests by merging source and target language structures, reducing bias and improving transfer performance.

Contribution

It proposes a new approach to unbiased cross-lingual relation extraction using code-mixed UD forests, addressing linguistic disparities between languages.

Findings

Significant performance improvements on ACE XRE benchmark datasets.

Effective reduction of transfer bias in cross-lingual relation extraction.

Demonstrated robustness across multiple language pairs.

Abstract

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.