Related papers: On Optimal Transformer Depth for Low-Resource Lang…

There exists a token imbalance phenomenon in natural language as different tokens appear with different frequencies, which leads to different learning difficulties for tokens in Neural Machine Translation (NMT). The vanilla NMT model…

Nearest Neighbor Machine Translation ($k$NN-MT) has achieved great success in domain adaptation tasks by integrating pre-trained Neural Machine Translation (NMT) models with domain-specific token-level retrieval. However, the reasons…

The effectiveness of Neural Machine Translation (NMT) models largely depends on the vocabulary used at training; small vocabularies can lead to out-of-vocabulary problems -- large ones, to memory issues. Subword (SW) tokenization has been…

Machine translation systems are expected to cope with various types of constraints in many practical scenarios. While neural machine translation (NMT) has achieved strong performance in unconstrained cases, it is non-trivial to impose…

Machine Translation System (MTS) serves as an effective tool for communication by translating text or speech from one language to another language. The need of an efficient translation system becomes obvious in a large multilingual…

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…

Neural machine translation (NMT) for low-resource local languages in Indonesia faces significant challenges, including the need for a representative benchmark and limited data availability. This work addresses these challenges by…

In this work, we compare the domain-specific translation performance of open-source autoregressive decoder-only large language models (LLMs) with task-oriented machine translation (MT) models. Our experiments focus on the medical domain and…

Large Transformer-based language models are pre-trained on corpora of varying sizes, for a different number of steps and with different batch sizes. At the same time, more fundamental components, such as the pre-training objective or…

Neural Machine Translation (NMT) performs poor on the low-resource language pair $(X,Z)$, especially when $Z$ is a rare language. By introducing another rich language $Y$, we propose a novel triangular training architecture (TA-NMT) to…

Neural machine translation, a recently proposed approach to machine translation based purely on neural networks, has shown promising results compared to the existing approaches such as phrase-based statistical machine translation. Despite…

Despite advancements in English-dominant generative large language models, further development is needed for low-resource languages to enhance global accessibility. The primary methods for representing these languages are monolingual and…

Machine translation (MT) is an important sub-field of natural language processing that aims to translate natural languages using computers. In recent years, end-to-end neural machine translation (NMT) has achieved great success and has…

Transformer has been widely adopted in Neural Machine Translation (NMT) because of its large capacity and parallel training of sequence generation. However, the deployment of Transformer is challenging because different scenarios require…

Transfer learning has been proven as an effective technique for neural machine translation under low-resource conditions. Existing methods require a common target language, language relatedness, or specific training tricks and regimes. We…

Despite advances in Neural Machine Translation (NMT), low-resource languages like Tigrinya remain underserved due to persistent challenges, including limited corpora, inadequate tokenization strategies, and the lack of standardized…

Neural Machine Translation (NMT) is resource intensive. We design a quantization procedure to compress NMT models better for devices with limited hardware capability. Because most neural network parameters are near zero, we employ…

Massively multilingual models for neural machine translation (NMT) are theoretically attractive, but often underperform bilingual models and deliver poor zero-shot translations. In this paper, we explore ways to improve them. We argue that…

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…

Low-resource machine translation (MT) presents a diversity of community needs and application challenges that remain poorly understood. To complement surveys and focus groups, which tend to rely on small samples of respondents, we propose…