paper-with-me

Papers

T-Modules: Translation Modules for Zero-Shot Cross-Modal Machine Translation

2022-05-24 · Paul-Ambroise Duquenne, Hongyu Gong, Benoît Sagot, Holger Schwenk

We present a new approach to perform zero-shot cross-modal transfer between speech and text for translation tasks. Multilingual speech and text are encoded in a joint fixed-size representation space. Then, we compare different approaches to decode these multimodal and multilingual fixed-size representations, enabling zero-shot translation between languages and modalities. All our models are trained without the need of cross-modal labeled translation data. Despite a fixed-size representation, we achieve very competitive results on several text and speech translation tasks. In particular, we significantly improve the state-of-the-art for zero-shot speech translation on Must-C. Incorporating a speech decoder in our framework, we introduce the first results for zero-shot direct speech-to-speech and text-to-speech translation.

📄 PDF Abstract BibTeX arXiv:2205.12216

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderMachine Translationtext-to-speechText to Speechtext-to-speech translationTranslation

Similar Papers 제목 키워드 기반

Revisiting Modularized Multilingual NMT to Meet Industrial Demands

2020-10-19 · EMNLP 2020 11 · Sungwon Lyu, Bokyung Son, Kichang Yang, Jaekyoung Bae

The complete sharing of parameters for multilingual translation (1-1) has been the mainstream approach in current research. However, degraded performance due to the capacity bottleneck and low maintainability hinders its…

Machine TranslationNMTTranslation

Improving Zero-shot Neural Machine Translation on Language-specific Encoders-Decoders

2021-02-12 · Junwei Liao, Yu Shi, Ming Gong, Linjun Shou 외

Recently, universal neural machine translation (NMT) with shared encoder-decoder gained good performance on zero-shot translation. Unlike universal NMT, jointly trained language-specific encoders-decoders aim to achieve …

DecoderDenoisingMachine TranslationNMT+1

From Bilingual to Multilingual Neural Machine Translation by Incremental Training

2019-06-28 · ACL 2019 7 · Carlos Escolano, Marta R. Costa-jussà, José A. R. Fonollosa

Multilingual Neural Machine Translation approaches are based on the use of task-specific models and the addition of one more language can only be done by retraining the whole system. In this work, we propose a new traini…

DecoderMachine TranslationTranslation

Multilingual Neural Machine Translation With the Right Amount of Sharing

2022-06-01 · EAMT 2022 6 · Taido Purason, Andre Tättar

Large multilingual Transformer-based machine translation models have had a pivotal role in making translation systems available for hundreds of languages with good zero-shot translation performance. One such example is t…

DecoderMachine TranslationNMTTranslation

Language and Task Arithmetic with Parameter-Efficient Layers for Zero-Shot Summarization

2023-11-15 · Alexandra Chronopoulou, Jonas Pfeiffer, Joshua Maynez, Xinyi Wang 외

Parameter-efficient fine-tuning (PEFT) using labeled task data can significantly improve the performance of large language models (LLMs) on the downstream task. However, there are 7000 languages in the world and many of …

Cross-Lingual Transferparameter-efficient fine-tuningTask ArithmeticText Generation+1