NTCIR-11 Math-2 Task Overview
نویسندگان
چکیده
•Mathematics plays a fundamental role in Science, Technology, and Engineering (learn from Math, apply for STEM) •Mathematical knowledge is rich in content, sophisticated in structure, and technical in presentation! •There is a lot of documents with maths – 120.000 journal articles per year in pure/applied math, 3.5 Million overall – 50 million science articles in 2010 with a doubling time of 8-15 years And this excludes gray literature, engineering, and school textbooks. – Even in the Renaissance, polymaths like Leonardo de Vinci were a rare exception. •We need IR support to deal with this! ( NTCIR-11 Math-2 Task) Math Markup e.g. in MathML and LATEX
منابع مشابه
NTCIR-10 Math Pilot Task Overview
This paper presents an overview of a new pilot task, the NTCIR Math Task, which is specifically dedicated to information access to mathematical content. In particular, the paper summarizes the subtasks addressed at the NTCIR Math Task as well as the main approaches deployed by the participating groups.
متن کاملTUW-IMP at the NTCIR-11 Math-2
The TUW-IMP team participated in the NTCIR-11 Math-2 task for retrieving mathematical formulae in scientific documents. This report describes our approach to solving the given math retrieval problem.
متن کاملICST Math Retrieval System for NTCIR-11 Math-2 Task
In NTCIR-11, the NTCIR-Math-2 Task is organized for mathematical information retrieval. This paper proposes an innovative system for efficient formula index and retrieval. We build a novel indexing and matching model, taking both textual and spatial similarities into consideration. Besides, a hierarchical technique is introduced to generate sub-trees from the semi-operator trees of formulae. Th...
متن کاملQUALIBETA at the NTCIR-11 Math 2 Task: An Attempt to Query Math Collections
This project introduces our first attempt to mathematical retrieval of formulae from a large collection for the NTCIR-11 Math 2 task. Our approach combined a feature-extracted sequence mechanism of the formulae and a sentence level representation of the text describing the formulae to model the collection. The feature-extracted sequences used were: the category of the formulae, the sets of iden...
متن کاملMathWebSearch at NTCIR-11
We present and analyze the results of the MATHWEBSEARCH (MWS) system in the Math-2 task in the NTCIR-11 Information Retrieval challenge. MWS is a content-based full-text search engine that focuses on low-latency query answering for interactive applications. It combines a powerful exact formula unification/matching with the fulltext search capabilities of ElasticSearch to achieve simultaneous fu...
متن کامل