arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2211.02849cs.AI
收藏

基于远程监督迭代训练的粗到细知识图谱领域自适应

Coarse-to-fine Knowledge Graph Domain Adaptation based on Distantly-supervised Iterative Training

South China University of Technology(华南理工大学);University of Georgia(佐治亚大学);Massachusetts General Hospital(麻省总医院);Harvard Medical School(哈佛医学院);University of Virginia(弗吉尼亚大学);Pinterest
Hongmin Cai, Wenxiong Liao, Zhengliang Liu, Yiyang Zhang, Xiaoke Huang, Siqi Ding, Hui Ren, Zihao Wu, Haixing Dai, Sheng Li, Lingfei Wu, Ninghao Liu, Quanzheng … 展开作者

Hongmin Cai, Wenxiong Liao, Zhengliang Liu, Yiyang Zhang, Xiaoke Huang, Siqi Ding, Hui Ren, Zihao Wu, Haixing Dai, Sheng Li, Lingfei Wu, Ninghao Liu, Quanzheng Li, Tianming Liu, Xiang Li

AI总结:

提出一个集成框架,利用远程监督和迭代训练策略,实现从生物医学到肿瘤学的粗到细知识图谱领域自适应,无需人工标注,实验证明高效可行。

摘要:

现代监督学习神经网络模型需要大量人工标注数据,这使得构建特定领域的知识图谱既耗时又费力。与此同时,尽管基于远程监督学习的命名实体识别和关系抽取已有大量研究,但从大规模文本集合中无需人工标注即可构建特定领域知识图谱仍是一个亟待解决的问题。为此,我们提出了一个集成框架,用于将知识图谱从一个粗粒度领域(生物医学)自适应并重新学习到一个更细定义的领域(肿瘤学)。在该框架中,我们将远程监督应用于跨领域知识图谱自适应,因此训练模型无需任何人工数据标注。我们引入了一种新颖的迭代训练策略,以促进领域特定命名实体和三元组的发现。实验结果表明,所提出的框架能够高效地执行领域自适应和知识图谱构建。

英文摘要:

Modern supervised learning neural network models require a large amount of manually labeled data, which makes the construction of domain-specific knowledge graphs time-consuming and labor-intensive. In parallel, although there has been much research on named entity recognition and relation extraction based on distantly supervised learning, constructing a domain-specific knowledge graph from large collections of textual data without manual annotations is still an urgent problem to be solved. In response, we propose an integrated framework for adapting and re-learning knowledge graphs from one coarse domain (biomedical) to a finer-define domain (oncology). In this framework, we apply distant-supervision on cross-domain knowledge graph adaptation. Consequently, no manual data annotation is required to train the model. We introduce a novel iterative training strategy to facilitate the discovery of domain-specific named entities and triples. Experimental results indicate that the proposed framework can perform domain adaptation and construction of knowledge graph efficiently.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑