Related papers: Active Learning for Massively Parallel Translation…
Existing curriculum learning approaches to Neural Machine Translation (NMT) require sampling sufficient amounts of "easy" samples from training data at the early training stage. This is not always achievable for low-resource languages where…
The scarcity of large parallel corpora is an important obstacle for neural machine translation. A common solution is to exploit the knowledge of language models (LM) trained on abundant monolingual data. In this work, we propose a novel…
Multilingual sentence representations pose a great advantage for low-resource languages that do not have enough data to build monolingual models on their own. These multilingual sentence representations have been separately exploited by few…
Recent studies have highlighted the potential of exploiting parallel corpora to enhance multilingual large language models, improving performance in both bilingual tasks, e.g., machine translation, and general-purpose tasks, e.g., text…
Extremely low-resource (XLR) languages lack substantial corpora for training NLP models, motivating the use of all available resources such as dictionaries and grammar books. Machine Translation from One Book (Tanzer et al., 2024) suggests…
While achieving state-of-the-art results in multiple tasks and languages, translation-based cross-lingual transfer is often overlooked in favour of massively multilingual pre-trained encoders. Arguably, this is due to its main limitations:…
General Large Language Models (LLMs) excel in reasoning, but those enhanced for translation struggle with reasoning tasks. To address this, we propose a novel translationenhanced recipe that begins with instruct models and applies…
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…
Large Language Models (LLMs) excel in high-resource languages but struggle with low-resource languages due to limited training data. This paper presents TALL (Trainable Architecture for Enhancing LLM Performance in Low-Resource Languages),…
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…
Large Language Models (LLM's) have demonstrated considerable success in various Natural Language Processing tasks, but they have yet to attain state-of-the-art performance in Neural Machine Translation (NMT). Nevertheless, their significant…
The data scarcity in low-resource languages has become a bottleneck to building robust neural machine translation systems. Fine-tuning a multilingual pre-trained model (e.g., mBART (Liu et al., 2020)) on the translation task is a good…
Recent studies in prompting large language model (LLM) for document-level machine translation (DMT) primarily focus on the inter-sentence context by flatting the source document into a long sequence. This approach relies solely on the…
The importance of qualitative parallel data in machine translation has long been determined but it has always been very difficult to obtain such in sufficient quantity for the majority of world languages, mainly because of the associated…
This paper proposes a novel technique that applies case-based reasoning in order to generate templates for reusable parse tree fragments, based on PoS tags of bigrams and trigrams that demonstrate low variability in their syntactic analyses…
We address for the first time unsupervised training for a translation task with hundreds of thousands of vocabulary words. We scale up the expectation-maximization (EM) algorithm to learn a large translation table without any parallel text…
Recognizing semantically similar sentences or paragraphs across languages is beneficial for many tasks, ranging from cross-lingual information retrieval and plagiarism detection to machine translation. Recently proposed methods for…
Despite impressive empirical successes of neural machine translation (NMT) on standard benchmarks, limited parallel data impedes the application of NMT models to many language pairs. Data augmentation methods such as back-translation make…
Conventional recommendation systems (RSs) are typically optimized to enhance performance metrics uniformly across all training samples. This makes it hard for data-driven RSs to cater to a diverse set of users due to the varying properties…
Current multilingual semantic parsing (MSP) datasets are almost all collected by translating the utterances in the existing datasets from the resource-rich language to the target language. However, manual translation is costly. To reduce…