On Target Segmentation for Direct Speech Translation

by   Mattia Antonino Di Gangi, et al.

Recent studies on direct speech translation show continuous improvements by means of data augmentation techniques and bigger deep learning models. While these methods are helping to close the gap between this new approach and the more traditional cascaded one, there are many incongruities among different studies that make it difficult to assess the state of the art. Surprisingly, one point of discussion is the segmentation of the target text. Character-level segmentation has been initially proposed to obtain an open vocabulary, but it results on long sequences and long training time. Then, subword-level segmentation became the state of the art in neural machine translation as it produces shorter sequences that reduce the training time, while being superior to word-level models. As such, recent works on speech translation started using target subwords despite the initial use of characters and some recent claims of better results at the character level. In this work, we perform an extensive comparison of the two methods on three benchmarks covering 8 language directions and multilingual training. Subword-level segmentation compares favorably in all settings, outperforming its character-level counterpart in a range of 1 to 3 BLEU points.


page 1

page 2

page 3

page 4


Fully Character-Level Neural Machine Translation without Explicit Segmentation

Most existing machine translation systems operate at the level of words,...

Towards Character-Level Transformer NMT by Finetuning Subword Systems

Applying the Transformer architecture on the character level usually req...

SegAugment: Maximizing the Utility of Speech Translation Data with Segmentation-based Augmentations

Data scarcity is one of the main issues with the end-to-end approach for...

Subword-Delimited Downsampling for Better Character-Level Translation

Subword-level models have been the dominant paradigm in NLP. However, ch...

KIT's Multilingual Speech Translation System for IWSLT 2023

Many existing speech translation benchmarks focus on native-English spee...

Robust Open-Vocabulary Translation from Visual Text Representations

Machine translation models have discrete vocabularies and commonly use s...

Please sign up or login with your details

Forgot password? Click here to reset