Knowledge Commons of Institute of Automation,CAS
PCEN: Potential Correlation-Enhanced Network for Multimodal Named Entity Recognition | |
Jiakai Geng1,2![]() ![]() ![]() ![]() ![]() | |
2023-11 | |
会议名称 | 2023 IEEE International Conference on Intelligence and Security Informatics (ISI) |
会议日期 | 02-03 October 2023 |
会议地点 | Charlotte, NC, USA |
摘要 | Multimodal Named Entity Recognition (MNER) in social media posts plays an important role in both security and natural language processing domains. Existing approaches mainly include extracting useful visual features from images, and integrating them into text representation for NER via multimodal fusion. Nevertheless, there is potential correlation among samples in the dataset, but is ignored by most of the existing studies. In this paper, we propose a potential correlation-enhanced network (PCEN) for MNER. Specifically, we (1) consider the potential correlation as an important visual feature for MNER, and (2) utilize it to guide the final recognition of entities. To tackle the first issue, we employ unsupervised clustering to divide the images of training samples into clusters, and take the trainable embedding of each cluster label as a visual feature because samples with the same cluster label have higher potential correlation. To tackle the second issue, we argue that the samples in the same cluster are more likely to have similar distributions of entity types in their text. We design an inconsistency loss to encourage the consistency between the entity recognition result of each sample and the pre-trained entity type distribution of the corresponding cluster this sample belongs to. Experiments on two MNER benchmarks demonstrate the effectiveness of our proposed method. |
关键词 | named entity recognition multimodal learning vision-language pre-trained model inconsistency loss |
DOI | 10.1109/ISI58743.2023.10297238 |
收录类别 | EI |
七大方向——子方向分类 | 多模态智能 |
国重实验室规划方向分类 | 人工智能基础前沿理论 |
是否有论文关联数据集需要存交 | 否 |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/57068 |
专题 | 舆论大数据科学与技术应用联合实验室 |
通讯作者 | Chenyang Zhang |
作者单位 | 1.State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Jiakai Geng,Chenyang Zhang,Linjing Li,et al. PCEN: Potential Correlation-Enhanced Network for Multimodal Named Entity Recognition[C],2023. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
PCEN_Potential_Corre(4985KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论