paper-with-me

Papers

Multilingual Unsupervised NMT using Shared Encoder and Language-Specific Decoders

2019-07-01 · ACL 2019 7 · Sukanta Sen, Kamal Kumar Gupta, Asif Ekbal, Pushpak Bhattacharyya

In this paper, we propose a multilingual unsupervised NMT scheme which jointly trains multiple languages with a shared encoder and multiple decoders. Our approach is based on denoising autoencoding of each language and back-translating between English and multiple non-English languages. This results in a universal encoder which can encode any language participating in training into an inter-lingual representation, and language-specific decoders. Our experiments using only monolingual corpora show that multilingual unsupervised model performs better than the separately trained bilingual models achieving improvement of up to 1.48 BLEU points on WMT test sets. We also observe that even if we do not train the network for all possible translation directions, the network is still able to translate in a many-to-many fashion leveraging encoder{'}s ability to generate interlingual representation.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingNMTTranslation

Similar Papers 제목 키워드 기반

NIT Rourkela Machine Translation(MT) System Submission to WAT 2022 for MultiIndicMT: An Indic Language Multilingual Shared Task

2022-10-01 · WAT 2022 10 · Sudhansu Bala Das, Atharv Biradar, Tapas Kumar Mishra, Bidyut Kumar Patra

Multilingual Neural Machine Translation (MNMT) exhibits incredible performance with the development of a single translation model for many languages. Previous studies on multilingual translation reveal that multilingual …

DecoderMachine TranslationNMTTranslation

Multilingual Machine Translation: Closing the Gap between Shared and Language-specific Encoder-Decoders

2020-04-14 · EACL 2021 2 · Carlos Escolano, Marta R. Costa-jussà, José A. R. Fonollosa, Mikel Artetxe

State-of-the-art multilingual machine translation relies on a universal encoder-decoder, which requires retraining the entire system to add new languages. In this paper, we propose an alternative approach that is based o…

DecoderLifelong learningMachine TranslationTranslation

Evaluating Multilingual Text Encoders for Unsupervised Cross-Lingual Retrieval

2021-01-21 · Robert Litschko, Ivan Vulić, Simone Paolo Ponzetto, Goran Glavaš

Pretrained multilingual text encoders based on neural Transformer architectures, such as multilingual BERT (mBERT) and XLM, have achieved strong performance on a myriad of language understanding tasks. Consequently, they…

Cross-Lingual Word EmbeddingsRepresentation LearningRetrievalSentence+2

Acoustic word embeddings for zero-resource languages using self-supervised contrastive learning and multilingual adaptation

2021-03-19 · Christiaan Jacobs, Yevgen Matusevych, Herman Kamper

Acoustic word embeddings (AWEs) are fixed-dimensional representations of variable-length speech segments. For zero-resource languages where labelled data is not available, one AWE approach is to use unsupervised autoenco…

Contrastive LearningWord Embeddings

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