paper-with-me

Papers

Multilingual Neural Machine Translation With Soft Decoupled Encoding

2019-02-09 · ICLR 2019 5 · Xinyi Wang, Hieu Pham, Philip Arthur, Graham Neubig

Multilingual training of neural machine translation (NMT) systems has led to impressive accuracy improvements on low-resource languages. However, there are still significant challenges in efficiently learning word representations in the face of paucity of data. In this paper, we propose Soft Decoupled Encoding (SDE), a multilingual lexicon encoding framework specifically designed to share lexical-level information intelligently without requiring heuristic preprocessing such as pre-segmenting the data. SDE represents a word by its spelling through a character encoding, and its semantic meaning through a latent embedding space shared by all languages. Experiments on a standard dataset of four low-resource languages show consistent improvements over strong multilingual NMT baselines, with gains of up to 2 BLEU on one of the tested languages, achieving the new state-of-the-art on all four language pairs.

📄 PDF Abstract BibTeX arXiv:1902.03499

Code (1)

cindyxinyiwang/SDE 공식 구현 pytorch

Tasks

Machine TranslationNMTTranslation

Similar Papers 제목 키워드 기반

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…

DecoderMachine TranslationNMTTranslation

Multilingual Machine Translation Systems from Microsoft for WMT21 Shared Task

2021-11-03 · WMT (EMNLP) 2021 11 · Jian Yang, Shuming Ma, Haoyang Huang, Dongdong Zhang 외

This report describes Microsoft's machine translation systems for the WMT21 shared task on large-scale multilingual machine translation. We participated in all three evaluation tracks including Large Track and two Small …

DecoderMachine TranslationTranslation

Multilingual Machine Translation with Quantum Encoder Decoder Attention-based Convolutional Variational Circuits

2025-05-14 · Subrit Dikshit, Ritu Tiwari, Priyank Jain

Cloud-based multilingual translation services like Google Translate and Microsoft Translator achieve state-of-the-art translation capabilities. These services inherently use large multilingual language models such as GRU…

DecoderMachine TranslationTranslation

LVP-M3: Language-aware Visual Prompt for Multilingual Multimodal Machine Translation

2022-10-19 · Hongcheng Guo, Jiaheng Liu, Haoyang Huang, Jian Yang 외

Multimodal Machine Translation (MMT) focuses on enhancing text-only translation with visual features, which has attracted considerable attention from both natural language processing and computer vision communities. Rece…

Machine TranslationMultimodal Machine TranslationTranslation

Vocabulary-informed Language Encoding

2022-10-01 · COLING 2022 10 · Xi Ai, Bin Fang

A Multilingual model relies on language encodings to identify input languages because the multilingual model has to distinguish between the input and output languages or among all the languages for cross-lingual tasks. F…

Machine TranslationTranslationWord Embeddings