Related papers: Shiksha: A Technical Domain focused Translation Da…
Image Translation (IT) holds immense potential across diverse domains, enabling the translation of textual content within images into various languages. However, existing datasets often suffer from limitations in scale, diversity, and…
Resources for the non-English languages are scarce and this paper addresses this problem in the context of machine translation, by automatically extracting parallel sentence pairs from the multilingual articles available on the Internet. In…
The training of topic models for a multilingual environment is a challenging task, requiring the use of sophisticated algorithms, topic-aligned corpora, and manual evaluation. These difficulties are further exacerbated when the developer…
The performance of Neural Machine Translation (NMT) depends significantly on the size of the available parallel corpus. Due to this fact, low resource language pairs demonstrate low translation performance compared to high resource language…
A rising interest in the modality extension of foundation language models warrants discussion on the most effective, and efficient, multimodal training approach. This work focuses on neural machine translation (NMT) and proposes a joint…
Neural machine translation (NMT) has arguably achieved human level parity when trained and evaluated at the sentence-level. Document-level neural machine translation has received less attention and lags behind its sentence-level…
Despite the considerable advancements in English LLMs, the progress in building comparable models for other languages has been hindered due to the scarcity of tailored resources. Our work aims to bridge this divide by introducing an…
Neural Machine Translation (NMT) has become a significant technology in natural language processing through extensive research and development. However, the deficiency of high-quality bilingual language pair data still poses a major…
Recent NLP advances focus primarily on standardized languages, leaving most low-resource dialects under-served especially in Indian scenarios. In India, the issue is particularly important: despite Hindi being the third most spoken language…
Existing document-level machine translation resources are only available for a handful of languages, mostly high-resourced ones. To facilitate the training and evaluation of document-level translation and, more broadly, long-context…
In neural machine translation (NMT), monolingual data in the target language are usually exploited through a method so-called "back-translation" to synthesize additional training parallel data. The synthetic data have been shown helpful to…
Unsupervised Neural Machine Translation (UNMT) focuses on improving NMT results under the assumption there is no human translated parallel data, yet little work has been done so far in highlighting its advantages compared to supervised…
Although all-in-one-model multilingual neural machine translation (multilingual NMT) has achieved remarkable progress, the convergence inconsistency in the joint training is ignored, i.e., different language pairs reaching convergence in…
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…
Machine translation systems achieve near human-level performance on some languages, yet their effectiveness strongly relies on the availability of large amounts of parallel sentences, which hinders their applicability to the majority of…
Machine Translation (MT) evaluation has gone beyond metrics, towards more specific linguistic phenomena. Regarding English-Chinese language pairs, passive sentences are constructed and distributed differently due to language variation, thus…
We investigate the following question for machine translation (MT): can we develop a single universal MT model to serve as the common seed and obtain derivative and improved models on arbitrary language pairs? We propose mRASP, an approach…
Pre-training models with large crawled corpora can lead to issues such as toxicity and bias, as well as copyright and privacy concerns. A promising way of alleviating such concerns is to conduct pre-training with synthetic tasks and data,…
Parallel datasets are vital for performing and evaluating any kind of multilingual task. However, in the cases where one of the considered language pairs is a low-resource language, the existing top-down parallel data such as corpora are…
Transfer learning or multilingual model is essential for low-resource neural machine translation (NMT), but the applicability is limited to cognate languages by sharing their vocabularies. This paper shows effective techniques to transfer a…