Graph-based Dependency Parsing with Graph Neural Networks

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F19%3A10427125" target="_blank" >RIV/00216208:11320/19:10427125 - isvavai.cz</a>

Result on the web

<a href="https://www.aclweb.org/anthology/P19-1237" target="_blank" >https://www.aclweb.org/anthology/P19-1237</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Graph-based Dependency Parsing with Graph Neural Networks

Original language description

We investigate the problem of efficiently incorporating high-order features into neural graph-based dependency parsing. Instead of explicitly extracting high-order features from intermediate parse trees, we develop a more powerful dependency tree node representation which captures high-order information concisely and efficiently. We use graph neural networks (GNNs) to learn the representations and discuss several new configurations of GNN&apos;s updating and aggregation functions. Experiments on PTB show that our parser achieves the best UAS and LAS on PTB (96.0%, 94.3%) among systems without using any external resources.

Czech name

—

Czech description

—

Type

O - Miscellaneous

CEP classification

—

OECD FORD branch

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

Project

—

Continuities

—

Publication year

2019

Confidentiality

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