Constructing Code-mixed Universal Dependency Forest for Unbiased Cross-lingual Relation Extraction
Fei, Hao, Zhang, Meishan, Zhang, Min, Chua, Tat-Seng
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Jun-4-2023
- Country:
- North America > United States
- California > Santa Clara County > Palo Alto (0.04)
- Asia
- Singapore (0.04)
- China
- Heilongjiang Province > Harbin (0.04)
- Guangdong Province > Shenzhen (0.04)
- North America > United States
- Genre:
- Research Report (0.84)
- Technology: