Neural Cross-Lingual Relation Extraction Based on Bilingual Word Embedding Mapping

TL;DR

This paper introduces a novel cross-lingual relation extraction method that leverages bilingual word embedding mapping to transfer models from resource-rich to resource-poor languages, achieving strong results with minimal bilingual data.

Contribution

It proposes a new bilingual embedding mapping technique enabling direct transfer of neural RE models across languages, reducing reliance on extensive annotated data.

Findings

High accuracy achieved with only 1K bilingual word pairs

Effective transfer across multiple target languages

Outperforms baseline methods in cross-lingual RE tasks

Abstract

Relation extraction (RE) seeks to detect and classify semantic relationships between entities, which provides useful information for many NLP applications. Since the state-of-the-art RE models require large amounts of manually annotated data and language-specific resources to achieve high accuracy, it is very challenging to transfer an RE model of a resource-rich language to a resource-poor language. In this paper, we propose a new approach for cross-lingual RE model transfer based on bilingual word embedding mapping. It projects word embeddings from a target language to a source language, so that a well-trained source-language neural network RE model can be directly applied to the target language. Experiment results show that the proposed approach achieves very good performance for a number of target languages on both in-house and open datasets, using a small bilingual dictionary with only 1K word pairs.