Improving the performance of graph based dependency parsing by guiding bi-affine layer with augmented global and local features

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3AE2K66JV3" target="_blank" >RIV/00216208:11320/23:E2K66JV3 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85148029592&doi=10.1016%2fj.iswa.2023.200190&partnerID=40&md5=9076de4c2f23b6d5f724e67a11bfd3bb" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85148029592&doi=10.1016%2fj.iswa.2023.200190&partnerID=40&md5=9076de4c2f23b6d5f724e67a11bfd3bb</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.iswa.2023.200190" target="_blank" >10.1016/j.iswa.2023.200190</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Improving the performance of graph based dependency parsing by guiding bi-affine layer with augmented global and local features

Popis výsledku v původním jazyce

"The growing interaction between humans and machines raises the necessity to more sophisticated tools for natural language understanding. Dependency parsing is crucial for capturing the semantics of a sentence. Although graph-based dependency parsing approaches outperform transition-based methods because they are not exposed to error propagation as their compeer, their feature space is comparatively limited. Thus, the main issue with graph-based parsing is how to expand the set of features to improve performance. In this research, we propose to expand the feature space of graph-based parsers. To benefit from the global meaning of the entire sentence content, we employee the sentence representation as an additional token feature. Also, to highlight local word collaborations that build sub-tree structures, we use convolutional neural network layers over token embeddings. We achieve the state-of-art results for Turkish, English, Hungarian, and Korean by getting the unlabeled and labeled attachment scores respectively on the test sets; 82.64% and 76.35% on Turkish IMST, 93.36% and 91.34% on English EWT, 90.85% and 87.39% on Hungarian Szeged, 92.44% and 89.58% on Korean GSD treebanks. Our experimental findings show that augmented global and local features empower the performance of graph-based dependency parsers. © 2023 The Author(s)"

Název v anglickém jazyce

Improving the performance of graph based dependency parsing by guiding bi-affine layer with augmented global and local features

Popis výsledku anglicky

"The growing interaction between humans and machines raises the necessity to more sophisticated tools for natural language understanding. Dependency parsing is crucial for capturing the semantics of a sentence. Although graph-based dependency parsing approaches outperform transition-based methods because they are not exposed to error propagation as their compeer, their feature space is comparatively limited. Thus, the main issue with graph-based parsing is how to expand the set of features to improve performance. In this research, we propose to expand the feature space of graph-based parsers. To benefit from the global meaning of the entire sentence content, we employee the sentence representation as an additional token feature. Also, to highlight local word collaborations that build sub-tree structures, we use convolutional neural network layers over token embeddings. We achieve the state-of-art results for Turkish, English, Hungarian, and Korean by getting the unlabeled and labeled attachment scores respectively on the test sets; 82.64% and 76.35% on Turkish IMST, 93.36% and 91.34% on English EWT, 90.85% and 87.39% on Hungarian Szeged, 92.44% and 89.58% on Korean GSD treebanks. Our experimental findings show that augmented global and local features empower the performance of graph-based dependency parsers. © 2023 The Author(s)"

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

"Intelligent Systems with Applications"

ISSN

2667-3053

e-ISSN

—

Svazek periodika

18

Číslo periodika v rámci svazku

2023

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

14

Strana od-do

1-14

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-85148029592