Efficiency Analysis of Deeplearning4J Neural Network Classifiers in Development of Transition Based Dependency Parsers

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10441821" target="_blank" >RIV/00216208:11320/21:10441821 - isvavai.cz</a>

Výsledek na webu

<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=GrskjOjZwP" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=GrskjOjZwP</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.2478/amset-2021-0006" target="_blank" >10.2478/amset-2021-0006</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Efficiency Analysis of Deeplearning4J Neural Network Classifiers in Development of Transition Based Dependency Parsers

Popis výsledku v původním jazyce

Dependency parsing is a complex process in natural language text processing, text to semantic transformation. The efficiency improvement of dependency parsing is a current and an active research area in the NLP community. The paper presents four transitionbased dependency parser models with implementation using DL4J classifiers. The efficiency of the proposed models were tested with Hungarian language corpora. The parsing model uses a data representation form based on lightweight embedding and a novel morphological-description-vector format is proposed for the input layer. Based on the test experiments on parsing Hungarian text documents, the proposed list-based transitions parsers outperform the widespread stack-based variants.

Název v anglickém jazyce

Efficiency Analysis of Deeplearning4J Neural Network Classifiers in Development of Transition Based Dependency Parsers

Popis výsledku anglicky

Dependency parsing is a complex process in natural language text processing, text to semantic transformation. The efficiency improvement of dependency parsing is a current and an active research area in the NLP community. The paper presents four transitionbased dependency parser models with implementation using DL4J classifiers. The efficiency of the proposed models were tested with Hungarian language corpora. The parsing model uses a data representation form based on lightweight embedding and a novel morphological-description-vector format is proposed for the input layer. Based on the test experiments on parsing Hungarian text documents, the proposed list-based transitions parsers outperform the widespread stack-based variants.

Druh

J_ost - Ostatní články v recenzovaných periodicích

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2021

Kód důvěrnosti údajů

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

Název periodika

Acta Marisiensis Seria Technologica [online]

ISSN

2668-4217

e-ISSN

—

Svazek periodika

18

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

RO - Rumunsko

Počet stran výsledku

7

Strana od-do

33-39

Kód UT WoS článku

—

EID výsledku v databázi Scopus

—