ARQMath Lab: An Incubator for Semantic Formula Search in zbMATH Open?
ARQMath Lab: An Incubator for Semantic Formula Search in zbMATH Open?
复制标题
ARQMath Lab：zbMATH 中语义公式搜索的孵化器 打开？
DOI：
--
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Bela Gipp
中科院分区：
文献类型：
--
作者：
Philipp Scharpf;M. Schubotz;André Greiner;Malte Ostendorff;O. Teschke;Bela Gipp
ZbMATH数据库包含400多万个书目条目。我们的目标是提供对这些条目的轻松访问。因此，我们维护不同的索引结构，包括公式索引。为了优化我们数据库中条目的可查找性，我们不断研究新的方法来满足我们用户的信息需求。我们相信，ARQMath评估的结果将产生新的见解，即哪些索引结构最适合满足数学信息需求。搜索引擎、推荐系统、抄袭检查软件和许多其他作用于数据库(如arxiv和zbMATH)的增值服务需要结合自然语言和公式语言。解决这一挑战的一种初始方法是通过实体链接来丰富大多数非结构化的文档数据。CLEF 2020的ARQMath任务旨在解决将来自Math Stack Exchange(MSE)的新发布的问题与社区已经回答的现有问题联系起来的问题。为了深入了解MSE的信息需求、答案和公式类型，我们对任务1和2进行了手动运行。此外，我们还探索了几种公式检索方法：对于任务2，例如模糊字符串搜索、k最近邻居，以及我们最近引入的使用文本搜索查询检索感兴趣的数学对象(MOI)的方法。任务结果表明，我们的自动化方法和我们的人工运行在比赛中都没有取得好的成绩。然而，人们对教学语言搜索返回的搜索结果的感知质量特别促使我们对教学语言进行进一步研究。
The zbMATH database contains more than 4 million bibliographic entries. We aim to provide easy access to these entries. Therefore, we maintain different index structures, including a formula index. To optimize the findability of the entries in our database, we continuously investigate new approaches to satisfy the information needs of our users. We believe that the findings from the ARQMath evaluation will generate new insights into which index structures are most suitable to satisfy mathematical information needs. Search engines, recommender systems, plagiarism checking software, and many other added-value services acting on databases such as the arXiv and zbMATH need to combine natural and formula language. One initial approach to address this challenge is to enrich the mostly unstructured document data via Entity Linking. The ARQMath Task at CLEF 2020 aims to tackle the problem of linking newly posted questions from Math Stack Exchange (MSE) to existing ones that were already answered by the community. To deeply understand MSE information needs, answer-, and formula types, we performed manual runs for tasks 1 and 2. Furthermore, we explored several formula retrieval methods: For task 2, such as fuzzy string search, k-nearest neighbors, and our recently introduced approach to retrieve Mathematical Objects of Interest (MOI) with textual search queries. The task results show that neither our automated methods nor our manual runs archived good scores in the competition. However, the perceived quality of the hits returned by the MOI search particularly motivates us to conduct further research about MOI.
DOI：
10.1007/978-3-030-45442-5_73
发表时间：
2020-03-24
期刊：
Advances in Information Retrieval
影响因子：
--
作者：
Mansouri B;Agarwal A;Oard D;Zanibbi R
通讯作者：
Zanibbi R
ARQMath 2020 概述：CLEF 数学问题答案检索实验室
DOI：
10.1007/978-3-030-58219-7_15
发表时间：
2020
期刊：
Proc. Conference and Labs of the Evaluation Forum (CLEF
影响因子：
--
作者：
Zanibbi, Richard;Oard, Douglas W.;Agarwal, Anurag;Mansouri, Behrooz
通讯作者：
Mansouri, Behrooz