Related papers: A Framework for Hierarchical Multilingual Machine …
In machine translation, we often try to collect resources to improve performance. However, most of the language pairs, such as Korean-Arabic and Korean-Vietnamese, do not have enough resources to train machine translation systems. In this…
We present an approach to neural machine translation (NMT) that supports multiple domains in a single model and allows switching between the domains when translating. The core idea is to treat text domains as distinct languages and use…
It is still challenging to build an AI system that can perform tasks that involve vision and language at human level. So far, researchers have singled out individual tasks separately, for each of which they have designed networks and…
The overall translation quality reached by current machine translation (MT) systems for high-resourced language pairs is remarkably good. Standard methods of evaluation are not suitable nor intended to uncover the many translation errors…
Neural approaches have achieved state-of-the-art accuracy on machine translation but suffer from the high cost of collecting large scale parallel data. Thus, a lot of research has been conducted for neural machine translation (NMT) with…
Quality Estimation (QE) of Machine Translation (MT) is a task to estimate the quality scores for given translation outputs from an unknown MT system. However, QE scores for low-resource languages are usually intractable and hard to collect.…
We investigate how large language models perform on low-resource languages by benchmarking eight LLMs across five experimental conditions in English, Kazakh, and Mongolian. Using 50 hand-crafted questions spanning factual, reasoning,…
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…
A large number of machine translation approaches have recently been developed to facilitate the fluid migration of content across languages. However, the literature suggests that many obstacles must still be dealt with to achieve better…
While there are more than 7000 languages in the world, most translation research efforts have targeted a few high-resource languages. Commercial translation systems support only one hundred languages or fewer, and do not make these models…
Multimodal machine translation is an attractive application of neural machine translation (NMT). It helps computers to deeply understand visual objects and their relations with natural languages. However, multimodal NMT systems suffer from…
Despite advances in the multilingual capabilities of Large Language Models (LLMs), their performance varies substantially across different languages and tasks. In multilingual retrieval-augmented generation (RAG)-based systems, knowledge…
Recent work demonstrates the potential of multilingual pretraining of creating one model that can be used for various tasks in different languages. Previous work in multilingual pretraining has demonstrated that machine translation systems…
We investigate the potential of LLM-generated synthetic data for improving low-resource Machine Translation (MT). Focusing on seven diverse target languages, we construct a document-level synthetic corpus from English Europarl, and extend…
Most work in NLP makes the assumption that it is desirable to develop solutions in the native language in question. There is consequently a strong trend towards building native language models even for low-resource languages. This paper…
We present a simple method to improve neural translation of a low-resource language pair using parallel data from a related, also low-resource, language pair. The method is based on the transfer method of Zoph et al., but whereas their…
Multilingual language models often perform unevenly across different languages due to limited generalization capabilities for some languages. This issue is significant because of the growing interest in making universal language models that…
Modern machine translation (MT) systems depend on large parallel corpora, often collected from the Internet. However, recent evidence indicates that (i) a substantial portion of these texts are machine-generated translations, and (ii) an…
Multilingual language models have shown decent performance in multilingual and cross-lingual natural language understanding tasks. However, the power of these multilingual models in code-switching tasks has not been fully explored. In this…
Large language models (LLMs) still struggle across tasks outside of high-resource languages. In this work, we investigate cross-lingual transfer to lower-resource languages where task-specific post-training data is scarce. Building on prior…