Math-Aware Search Interfaces for Digital Mathematical Libraries (DML)

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F16%3A00089346" target="_blank" >RIV/00216224:14330/16:00089346 - isvavai.cz</a>

Výsledek na webu

<a href="http://jointmathematicsmeetings.org/meetings/national/jmm2016/2181_intro" target="_blank" >http://jointmathematicsmeetings.org/meetings/national/jmm2016/2181_intro</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Math-Aware Search Interfaces for Digital Mathematical Libraries (DML)

Popis výsledku v původním jazyce

Search is an ubiquitous way of access to digital knowledge today and math is no exception. Re-searching using online digital libraries like arXiv.org or the European Digital Mathematics Library (EuDML, http://eudml.org/) needs specific tools allowing math-aware similarity search or formulae search in addition to the widespread textual keyword queries. We will reflect on the implementation and experience with two search modules that take into account math specifics: (i) advanced search supporting mathematical formulae in addition to text keyword queries and (ii) semantic similarity search. Similarity search allows to find semantically similar papers (using distributional semantics methods such as LDA or word vectors) to a given one to allow math-aware browsing. Experiments taking into account formulae for topic (MSC) representation will be discussed. Both modules have been deployed by the EuDML for more than 2 years now. We will share experience with their use scenarios.

Název v anglickém jazyce

Math-Aware Search Interfaces for Digital Mathematical Libraries (DML)

Popis výsledku anglicky

Search is an ubiquitous way of access to digital knowledge today and math is no exception. Re-searching using online digital libraries like arXiv.org or the European Digital Mathematics Library (EuDML, http://eudml.org/) needs specific tools allowing math-aware similarity search or formulae search in addition to the widespread textual keyword queries. We will reflect on the implementation and experience with two search modules that take into account math specifics: (i) advanced search supporting mathematical formulae in addition to text keyword queries and (ii) semantic similarity search. Similarity search allows to find semantically similar papers (using distributional semantics methods such as LDA or word vectors) to a given one to allow math-aware browsing. Experiments taking into account formulae for topic (MSC) representation will be discussed. Both modules have been deployed by the EuDML for more than 2 years now. We will share experience with their use scenarios.

Druh

O - Ostatní výsledky

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2016

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů