paper-with-me

Papers

Improving Target-side Lexical Transfer in Multilingual Neural Machine Translation

2020-10-04 · Findings of the Association for Computational Linguistics 2020 · Luyu Gao, Xinyi Wang, Graham Neubig

To improve the performance of Neural Machine Translation~(NMT) for low-resource languages~(LRL), one effective strategy is to leverage parallel data from a related high-resource language~(HRL). However, multilingual data has been found more beneficial for NMT models that translate from the LRL to a target language than the ones that translate into the LRLs. In this paper, we aim to improve the effectiveness of multilingual transfer for NMT models that translate \emph{into} the LRL, by designing a better decoder word embedding. Extending upon a general-purpose multilingual encoding method Soft Decoupled Encoding~\citep{SDE}, we propose DecSDE, an efficient character n-gram based embedding specifically designed for the NMT decoder. Our experiments show that DecSDE leads to consistent gains of up to 1.8 BLEU on translation from English to four different languages.

📄 PDF Abstract BibTeX arXiv:2010.01667

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderMachine TranslationNMTTranslation

Similar Papers 제목 키워드 기반

Universal Neural Machine Translation for Extremely Low Resource Languages

2018-02-15 · NAACL 2018 6 · Jiatao Gu, Hany Hassan, Jacob Devlin, Victor O. K. Li

In this paper, we propose a new universal machine translation approach focusing on languages with a limited amount of parallel data. Our proposed approach utilizes a transfer-learning approach to share lexical and senten…

Machine TranslationSentenceTransfer LearningTranslation

Adapting Monolingual Models: Data can be Scarce when Language Similarity is High

2021-05-06 · Findings (ACL) 2021 8 · Wietse de Vries, Martijn Bartelds, Malvina Nissim, Martijn Wieling

For many (minority) languages, the resources needed to train large models are not available. We investigate the performance of zero-shot transfer learning with as little data as possible, and the influence of language si…

POSPOS TaggingTransfer Learning

Multilingual Pre-training with Language and Task Adaptation for Multilingual Text Style Transfer

2022-03-16 · ACL 2022 5 · Huiyuan Lai, Antonio Toral, Malvina Nissim

We exploit the pre-trained seq2seq model mBART for multilingual text style transfer. Using machine translated data as well as gold aligned English sentences yields state-of-the-art results in the three target languages w…

Style TransferText Style Transfer

Multilingual pre-training with Language and Task Adaptation for Multilingual Text Style Transfer

2021-11-16 · ACL ARR November 2021 11 · Anonymous

We exploit the pre-trained seq2seq model mBART for multilingual text style transfer. Using machine translated data as well as gold aligned English sentences yields state-of-the-art results in the three target languages w…

Style TransferText Style Transfer

Understanding Cross-Lingual Syntactic Transfer in Multilingual Recurrent Neural Networks

2020-03-31 · NoDaLiDa 2021 5 · Prajit Dhar, Arianna Bisazza

It is now established that modern neural language models can be successfully trained on multiple languages simultaneously without changes to the underlying architecture. But what kind of knowledge is really shared among …

Cross-Lingual Transfer