Related papers: OCR Improves Machine Translation for Low-Resource …
An ongoing challenge in current natural language processing is how its major advancements tend to disproportionately favor resource-rich languages, leaving a significant number of under-resourced languages behind. Due to the lack of…
Prior works have demonstrated that a low-resource language pair can benefit from multilingual machine translation (MT) systems, which rely on many language pairs' joint training. This paper proposes two simple strategies to address the rare…
Recent work on multilingual neural machine translation reported competitive performance with respect to bilingual models and surprisingly good performance even on (zeroshot) translation directions not observed at training time. We…
Optical Character Recognition (OCR) for low-resource languages remains a significant challenge due to the scarcity of large-scale annotated training datasets. Languages such as Kashmiri, with approximately 7 million speakers and a complex…
Evaluating machine translation (MT) for low-resource languages poses a persistent challenge, primarily due to the limited availability of high quality reference translations. This issue is further exacerbated in languages with multiple…
Encoder-only languages models are frequently used for a variety of standard machine learning tasks, including classification and retrieval. However, there has been a lack of recent research for encoder models, especially with respect to…
This research article examines the effectiveness of various pretraining strategies for developing machine translation models tailored to low-resource languages. Although this work considers several low-resource languages, including…
In the current machine translation (MT) landscape, the Transformer architecture stands out as the gold standard, especially for high-resource language pairs. This research delves into its efficacy for low-resource language pairs including…
Since the dawn of the computing era, information has been represented digitally so that it can be processed by electronic computers. Paper books and documents were abundant and widely being published at that time; and hence, there was a…
While end-to-end neural machine translation (NMT) has achieved notable success in the past years in translating a handful of resource-rich language pairs, it still suffers from the data scarcity problem for low-resource language pairs and…
Recently proposed data collection frameworks for endangered language documentation aim not only to collect speech in the language of interest, but also to collect translations into a high-resource language that will render the collected…
Neural language models are the backbone of modern-day natural language processing applications. Their use on textual heritage collections which have undergone Optical Character Recognition (OCR) is therefore also increasing. Nevertheless,…
Previously, neural methods in grammatical error correction (GEC) did not reach state-of-the-art results compared to phrase-based statistical machine translation (SMT) baselines. We demonstrate parallels between neural GEC and low-resource…
Multilingual machine translation has recently been in vogue given its potential for improving machine translation performance for low-resource languages via transfer learning. Empirical examinations demonstrating the success of existing…
We propose a new paradigm for machine translation that is particularly useful for no-resource languages (those without any publicly available bilingual or monolingual corpora): LLM-RBMT (LLM-Assisted Rule Based Machine Translation). Using…
Large Multimodal Models (LMMs) have recently shown strong performance on Optical Character Recognition (OCR) tasks, demonstrating their promising capability in document literacy. However, their effectiveness in real-world applications…
Multimodal machine translation (MMT) aims to improve translation quality by incorporating information from other modalities, such as vision. Previous MMT systems mainly focus on better access and use of visual information and tend to…
Recent studies have shown that reinforcement learning (RL) is an effective approach for improving the performance of neural machine translation (NMT) system. However, due to its instability, successfully RL training is challenging,…
This study examines the cross-linguistic effectiveness of transfer learning for low-resource machine translation by fine-tuning models initially trained on typologically similar high-resource languages, using limited data from the target…
Monolingual data, being readily available in large quantities, has been used to upscale the scarcely available parallel data to train better models for automatic translation. Self-learning, where a model is made to learn from its output, is…