Text Analyzing of Aviation Safety Reports

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F16%3A00304880" target="_blank" >RIV/68407700:21230/16:00304880 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21260/16:00304880

Výsledek na webu

<a href="https://wikt-daz2016.fiit.stuba.sk/program/zbornik-konferencie/" target="_blank" >https://wikt-daz2016.fiit.stuba.sk/program/zbornik-konferencie/</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Text Analyzing of Aviation Safety Reports

Popis výsledku v původním jazyce

Aviation safety reports start to play a crucial role in understanding incidents and accidents in the aviation safety field. Automated text processing is necessary for simplification of the safety reporting process.This task can be acheived in diffe-rent ways, such as statistical, non-statistical or a combination of these techniques. In this paper, we are mainly focusing on non-statistical ones, by introducing our text processing scenario. We start with indexing of various aviation safety vocabularies that we are using as a backbone for this task. Next, the golden stan-dard corpus is prepared, including the testing process of several Linked Data Knowledge Extraction tools, with respect to a domain-specific vocabulary. Then, choosing the most accurate entity annotation tools and making them work toget-her, as well as with other features that we added, taking into consideration some very specific terms and abbreviations used in aviation field. The ultimate goal is to build a tool that will integrate several techniques inside in order to provide high precision reports’ annotations in aviation safety domain.

Název v anglickém jazyce

Text Analyzing of Aviation Safety Reports

Popis výsledku anglicky

Aviation safety reports start to play a crucial role in understanding incidents and accidents in the aviation safety field. Automated text processing is necessary for simplification of the safety reporting process.This task can be acheived in diffe-rent ways, such as statistical, non-statistical or a combination of these techniques. In this paper, we are mainly focusing on non-statistical ones, by introducing our text processing scenario. We start with indexing of various aviation safety vocabularies that we are using as a backbone for this task. Next, the golden stan-dard corpus is prepared, including the testing process of several Linked Data Knowledge Extraction tools, with respect to a domain-specific vocabulary. Then, choosing the most accurate entity annotation tools and making them work toget-her, as well as with other features that we added, taking into consideration some very specific terms and abbreviations used in aviation field. The ultimate goal is to build a tool that will integrate several techniques inside in order to provide high precision reports’ annotations in aviation safety domain.

Druh

D - Stať ve sborníku

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

Název statě ve sborníku

Proceedings in Informatics and Information Technologies - (WIKT & DaZ 2016) 11th Workshop on Intelligent and Knowledge Oriented Technologies 35th Conference on Data and Knowledge

ISBN

978-80-227-4619-9

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

115-120

Název nakladatele

Vydavatel'stvo STU

Místo vydání

Bratislava

Místo konání akce

Smolenice

Datum konání akce

3. 11. 2016

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—