Identifying Grammar Rules for Language Education with Dependency Parsing in German
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F19%3A10427140" target="_blank" >RIV/00216208:11320/19:10427140 - isvavai.cz</a>
Výsledek na webu
<a href="https://www.aclweb.org/anthology/W19-7712" target="_blank" >https://www.aclweb.org/anthology/W19-7712</a>
DOI - Digital Object Identifier
—
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
Identifying Grammar Rules for Language Education with Dependency Parsing in German
Popis výsledku v původním jazyce
We propose a method of determining the syntactic difficulty of a sentence, using syntactic patternsthat identify grammatical rules on dependency parses. We have constructed a novel querylanguage based on constraint-based dependency grammars and a grammar of German rules (relevantto primary school education) with patterns in our language. We annotated these rules witha difficulty score and grammatical prerequisites and built a matching algorithm that matches thedependency parse of a sentence in CoNLL-U format with its relevant syntactic patterns. Weachieved 96% precision and 95% recall on a manually annotated set of sentences, and our bestresults on using parses from four parsers are 88% and 84% respectively.
Název v anglickém jazyce
Identifying Grammar Rules for Language Education with Dependency Parsing in German
Popis výsledku anglicky
We propose a method of determining the syntactic difficulty of a sentence, using syntactic patternsthat identify grammatical rules on dependency parses. We have constructed a novel querylanguage based on constraint-based dependency grammars and a grammar of German rules (relevantto primary school education) with patterns in our language. We annotated these rules witha difficulty score and grammatical prerequisites and built a matching algorithm that matches thedependency parse of a sentence in CoNLL-U format with its relevant syntactic patterns. Weachieved 96% precision and 95% recall on a manually annotated set of sentences, and our bestresults on using parses from four parsers are 88% and 84% respectively.
Klasifikace
Druh
O - Ostatní výsledky
CEP obor
—
OECD FORD obor
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Návaznosti výsledku
Projekt
—
Návaznosti
—
Ostatní
Rok uplatnění
2019
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů