CUNI Non-Autoregressive System for the WMT 22 Efficient Translation Shared Task

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F22%3A10456995" target="_blank" >RIV/00216208:11320/22:10456995 - isvavai.cz</a>

Result on the web

<a href="https://statmt.org/wmt22/pdf/2022.wmt-1.64.pdf" target="_blank" >https://statmt.org/wmt22/pdf/2022.wmt-1.64.pdf</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

CUNI Non-Autoregressive System for the WMT 22 Efficient Translation Shared Task

Original language description

We present a non-autoregressive system submission to the WMT 22 Efficient Translation Shared Task. Our system was used by Helcl et al. (2022) in an attempt to provide fair comparison between non-autoregressive and autoregressive models. This submission is an effort to establish solid baselines along with sound evaluation methodology, particularly in terms of measuring the decoding speed. The model itself is a 12-layer Transformer model trained with connectionist temporal classification on knowledge-distilled dataset by a strong autoregressive teacher model.

Czech name

—

Czech description

—

Type

O - Miscellaneous

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

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2022

Confidentiality

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