English
Related papers

Related papers: TULUN: Transparent and Adaptable Low-resource Mach…

200 papers

Achieving consistent high-quality machine translation (MT) across diverse domains remains a significant challenge, primarily due to the limited and imbalanced parallel training data available in various domains. While large language models…

Computation and Language · Computer Science 2024-10-04 Tianxiang Hu , Pei Zhang , Baosong Yang , Jun Xie , Derek F. Wong , Rui Wang

Large language models (LLMs) have demonstrated remarkable potential in handling multilingual machine translation (MMT). In this paper, we systematically investigate the advantages and challenges of LLMs for MMT by answering two questions:…

Computation and Language · Computer Science 2024-06-17 Wenhao Zhu , Hongyi Liu , Qingxiu Dong , Jingjing Xu , Shujian Huang , Lingpeng Kong , Jiajun Chen , Lei Li

General translation models often still struggle to generate accurate translations in specialized domains. To guide machine translation practitioners and characterize the effectiveness of domain adaptation methods under different data…

Computation and Language · Computer Science 2022-06-03 Virginia Adams , Sandeep Subramanian , Mike Chrzanowski , Oleksii Hrinchuk , Oleksii Kuchaiev

No-resource languages - those with minimal or no digital representation - pose unique challenges for machine translation (MT). Unlike low-resource languages, which rely on limited but existent corpora, no-resource languages often have fewer…

Computation and Language · Computer Science 2025-06-03 Madhavendra Thakur

Multilingual Neural Machine Translation (MNMT) for low-resource languages (LRL) can be enhanced by the presence of related high-resource languages (HRL), but the relatedness of HRL usually relies on predefined linguistic assumptions about…

Computation and Language · Computer Science 2019-10-31 Surafel M. Lakew , Alina Karakanta , Marcello Federico , Matteo Negri , Marco Turchi

This paper addresses the limited transfer and adaptation capabilities of large language models in low-resource language scenarios. It proposes a unified framework that combines a knowledge transfer module with parameter-efficient…

Computation and Language · Computer Science 2025-07-03 Shuangquan Lyu , Yingnan Deng , Guiran Liu , Zhen Qi , Ruotong Wang

Large language models (LLMs) have significantly advanced various natural language processing (NLP) tasks. Recent research indicates that moderately-sized LLMs often outperform larger ones after task-specific fine-tuning. This study focuses…

Computation and Language · Computer Science 2024-10-14 Minghao Wu , Thuy-Trang Vu , Lizhen Qu , George Foster , Gholamreza Haffari

State-of-the-art neural machine translation (NMT) systems are data-hungry and perform poorly on new domains with no supervised data. As data collection is expensive and infeasible in many cases, domain adaptation methods are needed. In this…

Computation and Language · Computer Science 2020-06-09 Di Jin , Zhijing Jin , Joey Tianyi Zhou , Peter Szolovits

Learning general representations of text is a fundamental problem for many natural language understanding (NLU) tasks. Previously, researchers have proposed to use language model pre-training and multi-task learning to learn robust…

Computation and Language · Computer Science 2019-08-29 Zi-Yi Dou , Keyi Yu , Antonios Anastasopoulos

Neural machine translation (NMT) from Chinese to low-resource Southeast Asian languages remains severely constrained by the extreme scarcity of clean parallel corpora and the pervasive noise in existing mined data. This chronic shortage not…

Computation and Language · Computer Science 2026-04-07 Zhixiang Lu , Chong Zhang , Chenyu Xue , Angelos Stefanidis , Chong Li , Jionglong Su , Zhengyong Jiang

Learned metrics such as BLEURT have in recent years become widely employed to evaluate the quality of machine translation systems. Training such metrics requires data which can be expensive and difficult to acquire, particularly for…

Computation and Language · Computer Science 2023-02-08 Amirkeivan Mohtashami , Mauro Verzetti , Paul K. Rubenstein

This paper describes the machine translation system developed jointly by Baidu Research and Oregon State University for WMT 2019 Machine Translation Robustness Shared Task. Translation of social media is a very challenging problem, since…

Computation and Language · Computer Science 2019-06-25 Renjie Zheng , Hairong Liu , Mingbo Ma , Baigong Zheng , Liang Huang

Large language models (LLMs) have demonstrated strong performance in general-purpose machine translation, but their effectiveness in complex, domain-sensitive translation tasks remains underexplored. Recent advancements in Large Reasoning…

Computation and Language · Computer Science 2025-05-27 Yongshi Ye , Biao Fu , Chongxuan Huang , Yidong Chen , Xiaodong Shi

In many humanitarian scenarios, translation into severely low resource languages often does not require a universal translation engine, but a dedicated text-specific translation engine. For example, healthcare records, hygienic procedures,…

Computation and Language · Computer Science 2023-05-09 Zhong Zhou , Jan Niehues , Alex Waibel

This work investigates the in-context learning abilities of pretrained large language models (LLMs) when instructed to translate text from a low-resource language into a high-resource language as part of an automated machine translation…

Computation and Language · Computer Science 2024-10-28 Sara Court , Micha Elsner

Multilingual Neural Machine Translation (MNMT) models leverage many language pairs during training to improve translation quality for low-resource languages by transferring knowledge from high-resource languages. We study the quality of a…

Computation and Language · Computer Science 2022-12-06 Miguel Rios , Raluca-Maria Chereji , Alina Secara , Dragos Ciobanu

It has been shown that the performance of neural machine translation (NMT) drops starkly in low-resource conditions, underperforming phrase-based statistical machine translation (PBSMT) and requiring large amounts of auxiliary data to…

Computation and Language · Computer Science 2019-05-29 Rico Sennrich , Biao Zhang

Large multilingual pretrained language models (mPLMs) have become the de facto state of the art for cross-lingual transfer in NLP. However, their large-scale deployment to many languages, besides pretraining data scarcity, is also hindered…

Computation and Language · Computer Science 2023-04-19 Sukannya Purkayastha , Sebastian Ruder , Jonas Pfeiffer , Iryna Gurevych , Ivan Vulić

Traditional machine translation methods typically involve training models directly on large parallel corpora, with limited emphasis on specialized terminology. However, In specialized fields such as patent, finance, or biomedical domains,…

Computation and Language · Computer Science 2024-10-22 Sejoon Kim , Mingi Sung , Jeonghwan Lee , Hyunkuk Lim , Jorge Froilan Gimenez Perez

We show that Claude 3 Opus, a large language model (LLM) released by Anthropic in March 2024, exhibits stronger machine translation competence than other LLMs. Though we find evidence of data contamination with Claude on FLORES-200, we…

Computation and Language · Computer Science 2024-04-23 Maxim Enis , Mark Hopkins