图 书 馆
KADE:使用规则化多任务学习调整知识库和文档嵌入模型KADE: Aligning Knowledge Base and Document Embedding Models using Regularized Multi-Task Learning |
|
| 课程网址: | http://videolectures.net/iswc2018_baumgartner_kade_aligning_regul... |
| 主讲教师: | Matthias Baumgartner |
| 开课单位: | 苏黎世大学 |
| 开课时间: | 2018-10-23 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | Knowledge Bases (KBs) and textual documents contain rich and complementary information about real-world objects, as well as relations among them. While text documents describe entities in freeform, KBs organizes such information in a structured way. This makes these two forms to represent information hard to compare and integrate, limiting the possibility to use them jointly to improve predictive and analytical tasks. In this article, we study this problem, and we propose KADE, a solution based on a regularized multi-task learning of KB and document embeddings. KADE can potentially incorporate any KB and document embedding learning method. Our experiments on multiple datasets and methods show that KADE effectively aligns documents and entities embedding, while maintaining the characteristics of the embedding models. |
| 关 键 词: | 知识库（KB）; 丰富补充信息; 知识库和文档嵌入学习方法; 多个数据集和方法 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2022-12-30：cyh |
| 最后编审: | 2023-05-15：cyh |
| 阅读次数: | 31 |