Arbobanko - A Treebank for Esperanto

Eckhard Bick*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

26 Downloads (Pure)

Abstract

In this paper we describe and evaluate Arbobanko, a syntactic treebank for the artificial language Esperanto, as well as methods and tools used to produce the treebank. For an under-resourced language, the quality of automatic syntactic pre-annotation is of obvious importance, and by evaluating the parser associated with the treebank, we try to answer the question whether the language's extremely regular morphology and low lexical ambiguity carry over into a more regular syntax and higher parsing accuracy. On the linguistic side, the treebank allows us to address and quantify the typological issue of (free) word order in Esperanto.

Original languageEnglish
Title of host publicationComputational Linguistics and Intelligent Text Processing - 19th International Conference, CICLing 2018, Revised Selected Papers
EditorsAlexander Gelbukh
PublisherSpringer Science+Business Media
Publication date2023
Pages248-260
ISBN (Print)978-3-031-23803-1
ISBN (Electronic)978-3-031-23804-8
DOIs
Publication statusPublished - 2023
Event19th International Conference on Computational Linguistics and Intelligent Text Processing, CICLing 2018 - Hanoi, Viet Nam
Duration: 18. Mar 201824. Mar 2018

Conference

Conference19th International Conference on Computational Linguistics and Intelligent Text Processing, CICLing 2018
Country/TerritoryViet Nam
CityHanoi
Period18/03/201824/03/2018
SeriesLecture Notes in Computer Science
Volume13397
ISSN0302-9743

Keywords

  • Constraint grammar
  • Dependency grammar
  • Esperanto
  • Free word order languages
  • Syntactic parsing
  • Treebanks

Fingerprint

Dive into the research topics of 'Arbobanko - A Treebank for Esperanto'. Together they form a unique fingerprint.

Cite this