Isometric MT: Neural Machine Translation for Automatic Dubbing

12/16/2021
by   Surafel M. Lakew, et al.
0

Automatic dubbing (AD) is among the use cases where translations should fit a given length template in order to achieve synchronicity between source and target speech. For neural machine translation (MT), generating translations of length close to the source length (e.g. within +-10 preserving quality is a challenging task. Controlling NMT output length comes at a cost to translation quality which is usually mitigated with a two step approach of generation of n-best hypotheses and then re-ranking them based on length and quality. This work, introduces a self-learning approach that allows a transformer model to directly learn to generate outputs that closely match the source length, in short isometric MT. In particular, our approach for isometric MT does not require to generate multiple hypotheses nor any auxiliary scoring function. We report results on four language pairs (English - French, Italian, German, Spanish) with a publicly available benchmark based on TED Talk data. Both automatic and manual evaluations show that our self-learning approach to performs on par with more complex isometric MT approaches.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/23/2019

Controlling the Output Length of Neural Machine Translation

The recent advances introduced by neural machine translation (NMT) are r...
research
10/08/2021

Machine Translation Verbosity Control for Automatic Dubbing

Automatic dubbing aims at seamlessly replacing the speech in a video doc...
research
04/01/2021

Sampling and Filtering of Neural Machine Translation Distillation Data

In most of neural machine translation distillation or stealing scenarios...
research
05/12/2022

AppTek's Submission to the IWSLT 2022 Isometric Spoken Language Translation Task

To participate in the Isometric Spoken Language Translation Task of the ...
research
05/17/2023

Bring More Attention to Syntactic Symmetry for Automatic Postediting of High-Quality Machine Translations

Automatic postediting (APE) is an automated process to refine a given ma...
research
05/24/2022

Principled Paraphrase Generation with Parallel Corpora

Round-trip Machine Translation (MT) is a popular choice for paraphrase g...
research
10/19/2022

A Continuum of Generation Tasks for Investigating Length Bias and Degenerate Repetition

Language models suffer from various degenerate behaviors. These differ b...

Please sign up or login with your details

Forgot password? Click here to reset