| 融合混合嵌入与关系标签嵌入的三元组联合抽取方法 |
| |
| 引用本文： | 戴剑锋,陈星妤,董黎刚,蒋献.融合混合嵌入与关系标签嵌入的三元组联合抽取方法[J].电信科学,2023,39(2):132-144. |
| |
| 作者姓名： | 戴剑锋 陈星妤 董黎刚 蒋献 |
| |
| 作者单位： | 浙江工商大学，浙江 杭州 310018 |
| |
| 基金项目： | 国家社会科学基金资助项目(17BYY090);浙江省重点研发计划项目(2017C03058);浙江省“尖兵”“领雁”研发攻关计划项目(2023C03202) |
| |
| 摘 要： | 三元组抽取的目的是从非结构化的文本中获取实体与实体间的关系，并应用于下游任务。嵌入机制对三元组抽取模型的性能有很大影响，嵌入向量应包含与关系抽取任务密切相关的丰富语义信息。在中文数据集中，字词之间包含的信息有很大区别，为了改进由分词错误产生的语义信息丢失问题，设计了融合混合嵌入与关系标签嵌入的三元组联合抽取方法（HEPA），提出了采用字嵌入与词嵌入结合的混合嵌入方法，降低由分词错误产生的误差；在实体抽取层中添加关系标签嵌入机制，融合文本与关系标签，利用注意力机制来区分句子中实体与不同关系标签的相关性，由此提高匹配精度；采用指针标注的方法匹配实体，提高了对关系重叠三元组的抽取效果。在公开的Du IE数据集上进行了对比实验，相较于表现最好的基线模型（Cas Rel）,HEPA的F1值提升了2.8%。
|
| 关 键 词： | 三元组抽取 关系嵌入 BERT 注意力机制 指针标注 |
A triple joint extraction method combining hybrid embedding and relational label embedding |
| |
| Jianfeng DAI,Xingyu CHEN,Ligang DONG,Xian JIANG.A triple joint extraction method combining hybrid embedding and relational label embedding[J].Telecommunications Science,2023,39(2):132-144. |
| |
| Authors: | Jianfeng DAI Xingyu CHEN Ligang DONG Xian JIANG |
| |
| Affiliation: | Zhejiang Gongshang University, Hangzhou 310018, China |
| |
| Abstract: | The purpose of triple extraction is to obtain relationships between entities from unstructured text and apply them to downstream tasks.The embedding mechanism has a great impact on the performance of the triple extraction model, and the embedding vector should contain rich semantic information that is closely related to the relationship extraction task.In Chinese datasets, the information contained between words is very different, and in order to avoid the loss of semantic information problems generated by word separation errors, a triple joint extraction method combining hybrid embedding and relational label embedding (HEPA) was designed, and a hybrid embedding means that combines letter embedding and word embedding was proposed to reduce the errors generated by word separation errors.A relational embedding mechanism that fuses text and relational labels was added, and an attention mechanism was used to distinguish the relevance of entities in a sentence with different relational labels, thus improving the matching accuracy.The method of matching entities with pointer annotation was used, which improved the extraction effect on relational overlapping triples.Comparative experiments are conducted on the publicly available DuIE dataset, and the F1 value of HEPA is improved by 2.8% compared to the best performing baseline model (CasRel). |
| |
| Keywords: | triple extraction relational embedding BERT attention mechanism pointer annotation |
|
| 点击此处可从《电信科学》浏览原始摘要信息 |
|
点击此处可从《电信科学》下载全文 |
