paper-with-me

Papers

Mitigating Data Imbalance and Representation Degeneration in Multilingual Machine Translation

2023-05-22 · Wen Lai, Alexandra Chronopoulou, Alexander Fraser

Despite advances in multilingual neural machine translation (MNMT), we argue that there are still two major challenges in this area: data imbalance and representation degeneration. The data imbalance problem refers to the imbalance in the amount of parallel corpora for all language pairs, especially for long-tail languages (i.e., very low-resource languages). The representation degeneration problem refers to the problem of encoded tokens tending to appear only in a small subspace of the full space available to the MNMT model. To solve these two issues, we propose Bi-ACL, a framework that uses only target-side monolingual data and a bilingual dictionary to improve the performance of the MNMT model. We define two modules, named bidirectional autoencoder and bidirectional contrastive learning, which we combine with an online constrained beam search and a curriculum learning sampling strategy. Extensive experiments show that our proposed method is more effective both in long-tail languages and in high-resource languages. We also demonstrate that our approach is capable of transferring knowledge between domains and languages in zero-shot scenarios.

📄 PDF Abstract BibTeX arXiv:2305.12786

Code (1)

lavine-lmu/bi-acl 공식 구현 pytorch

Tasks

Contrastive LearningMachine TranslationTranslation

Similar Papers 제목 키워드 기반

Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models

2022-11-09 · CVPR 2023 1 · Patrick Schramowski, Manuel Brack, Björn Deiseroth, Kristian Kersting

Text-conditioned image generation models have recently achieved astonishing results in image quality and text alignment and are consequently employed in a fast-growing number of applications. Since they are highly data-d…

Image GenerationImage to text

An Isotropy Analysis in the Multilingual BERT Embedding Space

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

Several studies have explored various advantages of multilingual pre-trained models (e.g., multilingual BERT) in capturing shared linguistic knowledge. However, their limitations have not been paid enough attention to. I…

HLT-MT: High-resource Language-specific Training for Multilingual Neural Machine Translation

2022-07-11 · Jian Yang, Yuwei Yin, Shuming Ma, Dongdong Zhang 외

Multilingual neural machine translation (MNMT) trained in multiple language pairs has attracted considerable attention due to fewer model parameters and lower training costs by sharing knowledge among multiple languages.…

DecoderMachine TranslationTranslation

Self-Weighted Contrastive Learning among Multiple Views for Mitigating Representation Degeneration

2023-09-21 · NeurIPS 2023 11

Recently, numerous studies have demonstrated the effectiveness of contrastive learning (CL), which learns feature representations by pulling in positive samples while pushing away negative samples. Many successes of CL l…

NiuTrans.LMT: Toward Inclusive and Scalable Multilingual Machine Translation with LLMs

2025-11-10 · Yingfeng Luo, Ziqiang Xu, Yuxuan Ouyang, Murun Yang 외 arxiv

Large language models have significantly advanced Multilingual Machine Translation (MMT), yet scaling to many languages while keeping quality robust across directions remains challenging. In this paper, we identify a fai…

Cross-Lingual TransferMachine Translation