Work

Mind the Gap: Data Enrichment in Dependency Parsing of Elliptical Constructions

Year: 2018

Type: conference-paper

Abstract: In this paper, we focus on parsing rare and non-trivial constructions, in particular ellipsis.We report on several experiments in enrichment of training data for this specific construction, evaluated on five languages: Czech, English, Finnish, Russian and Slovak.These data enrichment methods draw upon self-training and tri-training, combined with a stratified sampling method mimicking the structural complexity of the original treebank.In addition, using these same methods, we also demonstrate small improvements over the CoNLL-17 parsing shared task winning system for four of the five languages, not only restricted to the elliptical constructions.

DOI: 10.18653/v1/w18-6006

Authors: Kira Droganova, Filip Ginter, Jenna Kanerva, Daniel Zeman

Institutions: Charles University, University of Turku

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Funders: Grantová Agentura, Univerzita Karlova, Grantová Agentura České Republiky, Nokia Foundation, China Scholarship Council

OpenAlex ID: W2911959277

FWCI: 0.509

Cites: 19

Cited by: 6

Related to: 10