Knowledge Commons of Institute of Automation,CAS
A Multi-Modal Neural Geometric Solver with Textual Clauses Parsed from Diagram | |
Zhang Ming-Liang1,2![]() ![]() ![]() | |
2023-07 | |
会议名称 | Proceedings of the 32nd International Joint Conference on Artificial Intelligence |
页码 | 3374-3382 |
会议日期 | 2023-7-19 |
会议地点 | 中国 澳门 |
摘要 | Geometry problem solving (GPS) is a high-level mathematical reasoning requiring the capacities of multi-modal fusion and geometric knowledge application. Recently, neural solvers have shown great potential in GPS but still be short in diagram presentation and modal fusion. In this work, we convert diagrams into basic textual clauses to describe diagram features effectively, and propose a new neural solver called PGPSNet to fuse multimodal information efficiently. Combining structural and semantic pre-training, data augmentation and self-limited decoding, PGPSNet is endowed with rich knowledge of geometry theorems and geometric representation, and therefore promotes geometric understanding and reasoning. In addition, to facilitate the research of GPS, we build a new large-scale and fine-annotated GPS dataset named PGPS9K, labeled with both fine-grained diagram annotation and interpretable solution program. Experiments on PGPS9K and an existing dataset Geometry3K validate the superiority of our method over the state-of-the-art neural solvers. |
收录类别 | EI |
语种 | 英语 |
是否为代表性论文 | 是 |
七大方向——子方向分类 | 知识表示与推理 |
国重实验室规划方向分类 | 认知决策知识体系 |
是否有论文关联数据集需要存交 | 是 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/55697 |
专题 | 多模态人工智能系统全国重点实验室 |
通讯作者 | Liu Cheng-Lin |
作者单位 | 1.MAIS, Institute of Automation of Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Zhang Ming-Liang,Yin Fei,Liu Cheng-Lin. A Multi-Modal Neural Geometric Solver with Textual Clauses Parsed from Diagram[C],2023:3374-3382. |
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 | ||
0376.pdf(1110KB) | 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