Revisiting Tri-training of Dependency Parsers

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10442278" target="_blank" >RIV/00216208:11320/21:10442278 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Revisiting Tri-training of Dependency Parsers

Original language description

We compare two orthogonal semi-supervised learning techniques, namely tri-training and pretrained word embeddings, in the task of dependency parsing. We explore language-specific FastText and ELMo embeddings and multilingual BERT embeddings. We focus on a low resource scenario as semi-supervised learning can be expected to have the most impact here. Based on treebank size and available ELMo models, we select Hungarian, Uyghur (a zero-shot language for mBERT) and Vietnamese. Furthermore, we include English in a simulated low-resource setting. We find that pretrained word embeddings make more effective use of unlabelled data than tri-training but that the two approaches can be successfully combined.

Czech name

—

Czech description

—

Type

D - Article in proceedings

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

2021

Confidentiality

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

Article name in the collection

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

ISBN

978-1-955917-09-4

ISSN

—

e-ISSN

—

Number of pages

17

Pages from-to

9457-9473

Publisher name

Association for Computational Linguistics

Place of publication

Stroudsburg

Event location

Punta Cana

Event date

Nov 7, 2021

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—