Corpus ID: 226236679

Enabling Zero-shot Multilingual Spoken Language Translation with Language-Specific Encoders and Decoders

@article{Escolano2020EnablingZM,
  title={Enabling Zero-shot Multilingual Spoken Language Translation with Language-Specific Encoders and Decoders},
  author={Carlos Escolano and Marta Ruiz Costa-juss{\`a} and Jos{\'e} A. R. Fonollosa and Carlos Segura},
  journal={ArXiv},
  year={2020},
  volume={abs/2011.01097}
}
Current end-to-end approaches to Spoken Language Translation (SLT) rely on limited training resources, especially for multilingual settings. On the other hand, Multilingual Neural Machine Translation (MultiNMT) approaches rely on higher quality and more massive data sets. Our proposed method extends a MultiNMT architecture based on language-specific encoders-decoders to the task of Multilingual SLT (MultiSLT) Our experiments on four different languages show that coupling the speech encoder to… Expand

Figures and Tables from this paper

End-to-End Speech Translation with Pre-trained Models and Adapters: UPC at IWSLT 2021
TLDR
This paper describes the submission to the IWSLT 2021 offline speech translation task by the UPC Machine Translation group, which is an end-to-end speech translation system, which combines pre-trained models with coupling modules between the encoder and decoder, and uses an efficient fine-tuning technique. Expand
UPC's Speech Translation System for IWSLT 2021
TLDR
This paper describes the submission to the IWSLT 2021 offline speech translation task by the UPC Machine Translation group, which is an end-to-end speech translation system, which combines pre-trained models with coupling modules between the encoder and decoder, and uses an efficient fine-tuning technique. Expand
FINDINGS OF THE IWSLT 2021 EVALUATION CAMPAIGN
TLDR
This paper describes each shared task, data and evaluation metrics, and reports results of the received submissions of the IWSLT 2021 evaluation campaign. Expand
Lightweight Adapter Tuning for Multilingual Speech Translation
TLDR
This paper proposes a comprehensive analysis of adapters for multilingual speech translation (ST) and shows that adapters can be used to efficiently specialize ST to specific language pairs with a low extra cost in terms of parameters. Expand

References

SHOWING 1-10 OF 26 REFERENCES
Attention is All you Need
TLDR
A new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely is proposed, which generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data. Expand
Bleu: a Method for Automatic Evaluation of Machine Translation
TLDR
This work proposes a method of automatic machine translation evaluation that is quick, inexpensive, and language-independent, that correlates highly with human evaluation, and that has little marginal cost per run. Expand
One-to-Many Multilingual End-to-End Speech Translation
TLDR
This paper proposes a variant of end-to-end SLT that uses target-language embed-dings to shift the input representations in different portions of the space according to the language, so to better support the production of output in the desired target language. Expand
Neural Machine Translation of Rare Words with Subword Units
TLDR
This paper introduces a simpler and more effective approach, making the NMT model capable of open-vocabulary translation by encoding rare and unknown words as sequences of subword units, and empirically shows that subword models improve over a back-off dictionary baseline for the WMT 15 translation tasks English-German and English-Russian by 1.3 BLEU. Expand
Multilingual Machine Translation: Closing the Gap between Shared and Language-specific Encoder-Decoders
TLDR
This work proposes an alternative approach that is based on language-specific encoder-decoders, and can thus be more easily extended to new languages by learning their corresponding modules, advancing toward modular multilingual machine translation systems that can be flexibly extended in lifelong learning settings. Expand
From bilingual to multilingual neural‐based machine translation by incremental training
TLDR
A new architecture based on introducing an interlingual loss as an additional training objective is proposed, capable of reducing the number of production systems, with respect to thenumber of languages, from quadratic to linear; incrementally adding a new language to the system without retraining the languages already there; and allowing for translations from the newlanguage to all the others present in the system. Expand
Multilingual Speech Translation from Efficient Finetuning of Pretrained Models
We present a simple yet effective approach to build multilingual speech-to-text (ST) translation by efficient transfer learning from pretrained speech encoder and text decoder. Our key finding isExpand
CoVoST: A Diverse Multilingual Speech-To-Text Translation Corpus
TLDR
This work introduces CoVoST, a multilingual speech-to-text translation corpus from 11 languages into English, diversified with over 11,000 speakers and over 60 accents, and describes the dataset creation methodology and provides empirical evidence of the quality of the data. Expand
On the Cross-lingual Transferability of Monolingual Representations
TLDR
This work designs an alternative approach that transfers a monolingual model to new languages at the lexical level and shows that it is competitive with multilingual BERT on standard cross-lingUAL classification benchmarks and on a new Cross-lingual Question Answering Dataset (XQuAD). Expand
The TALP-UPC System Description for WMT20 News Translation Task: Multilingual Adaptation for Low Resource MT
TLDR
The TALP-UPC participation in the WMT20 news translation shared task for Tamil-English is described and iterative backtranslation is used to fine-tune the system and benefit from the monolingual data available. Expand
...
1
2
3
...