@article{Kong2025, 
author = {Ling-Xing Kong and You-Gang Chu and Zheng Ma and Jian-Bing Zhang and Jia-Jun Chen},
title = {Mix-Lingual Relation Extraction: Dataset and a Training Approach},
year = {2025},
journal = {Journal of Computer Science and Technology},
volume = {40},
number = {1},
pages = {42-59},
keywords = {natural language processing (NLP), code-switching, large language model (LLM), relation extraction, human-annotated dataset},
url = {https://www.sciopen.com/article/10.1007/s11390-024-4314-y},
doi = {10.1007/s11390-024-4314-y},
abstract = {Relation extraction is a pivotal task within the field of natural language processing, boasting numerous real-world applications. Existing research predominantly centers on monolingual relation extraction or cross-lingual enhancement for relation extraction. However, there exists a notable gap in understanding relation extraction within mix-lingual (or code-switching) scenarios. In these scenarios, individuals blend content from different languages within sentences, generating mix-lingual content. The effectiveness of existing relation extraction models in such scenarios remains largely unexplored due to the absence of dedicated datasets. To address this gap, we introduce the Mix-Lingual Relation Extraction (MixRE) task and construct a human-annotated dataset MixRED to support this task. Additionally, we propose a hierarchical training approach for the mix-lingual scenario named Mix-Lingual Training (MixTrain), designed to enhance the performance of large language models (LLMs) when capturing relational dependencies from mix-lingual content spanning different semantic levels. Our experiments involve evaluating state-of-the-art supervised models and LLMs on the constructed dataset, with results indicating that MixTrain notably improves model performance. Moreover, we investigate the effectiveness of using mix-lingual content as a tool to transfer learned relational dependencies across different languages. Additionally, we delve into factors influencing model performance for both supervised models and LLMs in the novel MixRE task.}
}