Integrating graph embedding and neural models for improving transition-based dependency parsing
Identifikátory výsledku
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>
Alternativní jazyky
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."
Klasifikace
Druh
J<sub>SC</sub> - 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)
Návaznosti výsledku
Projekt
—
Návaznosti
—
Ostatní
Rok uplatnění
2023
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
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