Character Transformations for Non-Autoregressive GEC Tagging
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10440578" target="_blank" >RIV/00216208:11320/21:10440578 - isvavai.cz</a>
Result on the web
<a href="https://aclanthology.org/2021.wnut-1.46/" target="_blank" >https://aclanthology.org/2021.wnut-1.46/</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Character Transformations for Non-Autoregressive GEC Tagging
Original language description
We propose a character-based non-autoregressive GEC approach, with automatically generated character transformations. Recently, per-word classification of correction edits has proven an efficient, parallelizable alternative to current encoder-decoder GEC systems. We show that word replacement edits may be suboptimal and lead to explosion of rules for spelling, diacritization and errors in morphologically rich languages, and propose a method for generating character transformations from GEC corpus. Finally, we train character transformation models for Czech, German and Russian, reaching solid results and dramatic speedup compared to autoregressive systems. The source code is released at https://github.com/ufal/wnut2021_character_transformations_gec.
Czech name
—
Czech description
—
Classification
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)
Result continuities
Project
<a href="/en/project/LM2018101" target="_blank" >LM2018101: Digital Research Infrastructure for the Language Technologies, Arts and Humanities</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach
Others
Publication year
2021
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the 7th Workshop on Noisy User-generated Text (W-NUT 2021)
ISBN
978-1-954085-90-9
ISSN
—
e-ISSN
—
Number of pages
6
Pages from-to
417-422
Publisher name
Association for Computational Linguistics
Place of publication
Stroudsburg, PA, USA
Event location
Online
Event date
Nov 11, 2021
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—