Empirical Analysis for Unsupervised Universal Dependency Parse Tree Aggregation

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3AFHKLLZB5" target="_blank" >RIV/00216208:11320/25:FHKLLZB5 - isvavai.cz</a>

Result on the web

<a href="https://arxiv.org/abs/2403.19183" target="_blank" >https://arxiv.org/abs/2403.19183</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.48550/arXiv.2403.19183" target="_blank" >10.48550/arXiv.2403.19183</a>

Result language

angličtina

Original language name

Empirical Analysis for Unsupervised Universal Dependency Parse Tree Aggregation

Original language description

Dependency parsing is an essential task in NLP, and the quality of dependency parsers is crucial for many downstream tasks. Parsers' quality often varies depending on the domain and the language involved. Therefore, it is essential to combat the issue of varying quality to achieve stable performance. In various NLP tasks, aggregation methods are used for post-processing aggregation and have been shown to combat the issue of varying quality. However, aggregation methods for post-processing aggregation have not been sufficiently studied in dependency parsing tasks. In an extensive empirical study, we compare different unsupervised post-processing aggregation methods to identify the most suitable dependency tree structure aggregation method.

Czech name

—

Czech description

—

Type

J_ost - Miscellaneous article in a specialist periodical

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

2024

Confidentiality

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

Name of the periodical

ArXiv

ISSN

2331-8422

e-ISSN

—

Volume of the periodical

2024

Issue of the periodical within the volume

2024

Country of publishing house

US - UNITED STATES

Number of pages

11

Pages from-to

1-11

UT code for WoS article

—

EID of the result in the Scopus database

—