paper-with-me

홈 › Papers

Multilingual Pixel Representations for Translation and Effective Cross-lingual Transfer

2023-05-23 · Elizabeth Salesky, Neha Verma, Philipp Koehn, Matt Post

We introduce and demonstrate how to effectively train multilingual machine translation models with pixel representations. We experiment with two different data settings with a variety of language and script coverage, demonstrating improved performance compared to subword embeddings. We explore various properties of pixel representations such as parameter sharing within and across scripts to better understand where they lead to positive transfer. We observe that these properties not only enable seamless cross-lingual transfer to unseen scripts, but make pixel representations more data-efficient than alternatives such as vocabulary expansion. We hope this work contributes to more extensible multilingual models for all languages and scripts.

📄 PDF Abstract BibTeX arXiv:2305.14280

Code (0)

등록된 구현이 없습니다.

Tasks

Cross-Lingual TransferMachine TranslationTranslation

Similar Papers 제목 키워드 기반

Towards a Deep Understanding of Multilingual End-to-End Speech Translation

2023-10-31 · Haoran Sun, Xiaohu Zhao, Yikun Lei, Shaolin Zhu 외

In this paper, we employ Singular Value Canonical Correlation Analysis (SVCCA) to analyze representations learnt in a multilingual end-to-end speech translation model trained over 22 languages. SVCCA enables us to estima…

Machine TranslationTranslation

Evaluating the Cross-Lingual Effectiveness of Massively Multilingual Neural Machine Translation

2019-09-01 · Aditya Siddhant, Melvin Johnson, Henry Tsai, Naveen Arivazhagan 외

The recently proposed massively multilingual neural machine translation (NMT) system has been shown to be capable of translating over 100 languages to and from English within a single model. Its improved translation perf…

Cross-Lingual TransferMachine TranslationNMTTransfer Learning+1

Analyzing and Improving Cross-lingual Knowledge Transfer for Machine Translation

2026-01-07 · David Stap arxiv

Multilingual machine translation systems aim to make knowledge accessible across languages, yet learning effective cross-lingual representations remains challenging. These challenges are especially pronounced for low-res…

Machine Translation

Overcoming Vocabulary Constraints with Pixel-level Fallback

2025-04-02 · Jonas F. Lotz, Hendra Setiawan, Stephan Peitz, Yova Kementchedjhieva

Subword tokenization requires balancing computational efficiency and vocabulary coverage, which often leads to suboptimal performance on languages and scripts not prioritized during training. We propose to augment pretra…

Computational EfficiencyCross-Lingual TransferMachine Translation

Can Domains Be Transferred Across Languages in Multi-Domain Multilingual Neural Machine Translation?

2022-10-20 · Thuy-Trang Vu, Shahram Khadivi, Xuanli He, Dinh Phung 외

Previous works mostly focus on either multilingual or multi-domain aspects of neural machine translation (NMT). This paper investigates whether the domain information can be transferred across languages on the compositio…

Machine TranslationNMTTAGTranslation