Integrating graph embedding and neural models for improving transition-based dependency parsing

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3ADP3UGVQB" target="_blank" >RIV/00216208:11320/23:DP3UGVQB - isvavai.cz</a>

Výsledek na webu

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85178157836&doi=10.1007%2fs00521-023-09223-3&partnerID=40&md5=d673340f56fbc637987bfe6b5b11b923" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85178157836&doi=10.1007%2fs00521-023-09223-3&partnerID=40&md5=d673340f56fbc637987bfe6b5b11b923</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s00521-023-09223-3" target="_blank" >10.1007/s00521-023-09223-3</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Integrating graph embedding and neural models for improving transition-based dependency parsing

Popis výsledku v původním jazyce

"This paper introduces an effective method for improving dependency parsing which is based on a graph embedding model. The model helps extract local and global connectivity patterns between tokens. This method allows neural network models to perform better on dependency parsing benchmarks. We propose to incorporate node embeddings trained by a graph embedding algorithm into a bidirectional recurrent neural network scheme. The new model outperforms a baseline reference using a state-of-the-art method on three dependency treebanks for both low-resource and high-resource natural languages, namely Indonesian, Vietnamese and English. We also show that the popular pretraining technique of BERT would not pick up on the same kind of signal as graph embeddings. The new parser together with all trained models is made available under an open-source license, facilitating community engagement and advancement of natural language processing research for two low-resource languages with around 300 million users worldwide in total. © 2023, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature."

Název v anglickém jazyce

Integrating graph embedding and neural models for improving transition-based dependency parsing

Popis výsledku anglicky

"This paper introduces an effective method for improving dependency parsing which is based on a graph embedding model. The model helps extract local and global connectivity patterns between tokens. This method allows neural network models to perform better on dependency parsing benchmarks. We propose to incorporate node embeddings trained by a graph embedding algorithm into a bidirectional recurrent neural network scheme. The new model outperforms a baseline reference using a state-of-the-art method on three dependency treebanks for both low-resource and high-resource natural languages, namely Indonesian, Vietnamese and English. We also show that the popular pretraining technique of BERT would not pick up on the same kind of signal as graph embeddings. The new parser together with all trained models is made available under an open-source license, facilitating community engagement and advancement of natural language processing research for two low-resource languages with around 300 million users worldwide in total. © 2023, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature."

Druh

J_SC - Článek v periodiku v databázi SCOPUS

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

2023

Kód důvěrnosti údajů

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

Název periodika

"Neural Computing and Applications"

ISSN

0941-0643

e-ISSN

—

Svazek periodika

""

Číslo periodika v rámci svazku

2023

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

18

Strana od-do

2999-3016

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-85178157836