PPT: Parsimonious Parser Transfer for Unsupervised Cross-Lingual Adaptation

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10442223" target="_blank" >RIV/00216208:11320/21:10442223 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

PPT: Parsimonious Parser Transfer for Unsupervised Cross-Lingual Adaptation

Original language description

Cross-lingual transfer is a leading technique for parsing low-resource languages in the absence of explicit supervision. Simple &apos;direct transfer&apos; of a learned model based on a multilingual input encoding has provided a strong benchmark. This paper presents a method for unsupervised cross-lingual transfer that improves over direct transfer systems by using their output as implicit supervision as part of self-training on unlabelled text in the target language. The method assumes minimal resources and provides maximal flexibility by (a) accepting any pre-trained arc-factored dependency parser; (b) assuming no access to source language data; (c) supporting both projective and non-projective parsing; and (d) supporting multi-source transfer. With English as the source language, we show significant improvements over state-of-the-art transfer models on both distant and nearby languages, despite our conceptually simpler approach. We provide analyses of the choice of source languages for multi-source transfer, and the advantage of non-projective parsing. Our code is available online.

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 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume

ISBN

978-1-954085-02-2

ISSN

—

e-ISSN

—

Number of pages

12

Pages from-to

2907-2918

Publisher name

Association for Computational Linguistics

Place of publication

Stroudsburg

Event location

online

Event date

Apr 19, 2021

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—