What Taggers Fail to Learn, Parsers Need the Most

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10442290" target="_blank" >RIV/00216208:11320/21:10442290 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

What Taggers Fail to Learn, Parsers Need the Most

Original language description

We present an error analysis of neural UPOS taggers to evaluate why using gold tags has such a large positive contribution to parsing performance while using predicted UPOS either harms performance or offers a negligible improvement. We also evaluate what neural dependency parsers implicitly learn about word types and how this relates to the errors taggers make, to explain the minimal impact using predicted tags has on parsers. We then mask UPOS tags based on errors made by taggers to tease away the contribution of UPOS tags that taggers succeed and fail to classify correctly and the impact of tagging errors.

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 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)

ISBN

978-91-7929-614-8

ISSN

—

e-ISSN

—

Number of pages

6

Pages from-to

309-314

Publisher name

Linköping University Electronic Press

Place of publication

Linköping

Event location

Reykjavik

Event date

May 31, 2021

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—