Dynamic Multi-View Fusion Mechanism For Chinese Relation Extraction
This work improves Chinese relation extraction for natural language processing applications, but it is incremental as it builds on existing methods by better integrating internal and external knowledge.
The paper tackled the problem of Chinese relation extraction by addressing the neglect of internal character information and noisy external knowledge, proposing a mixture-of-view-experts framework (MoVE) that dynamically learns multi-view features, resulting in consistent and significant superiority and robustness on three real-world datasets.
Recently, many studies incorporate external knowledge into character-level feature based models to improve the performance of Chinese relation extraction. However, these methods tend to ignore the internal information of the Chinese character and cannot filter out the noisy information of external knowledge. To address these issues, we propose a mixture-of-view-experts framework (MoVE) to dynamically learn multi-view features for Chinese relation extraction. With both the internal and external knowledge of Chinese characters, our framework can better capture the semantic information of Chinese characters. To demonstrate the effectiveness of the proposed framework, we conduct extensive experiments on three real-world datasets in distinct domains. Experimental results show consistent and significant superiority and robustness of our proposed framework. Our code and dataset will be released at: https://gitee.com/tmg-nudt/multi-view-of-expert-for-chineserelation-extraction