Related papers: TranslateGemma Technical Report

Fine-tuning multilingual sequence-to-sequence large language models (msLLMs) has shown promise in developing neural machine translation (NMT) systems for low-resource languages (LRLs). However, conventional single-stage fine-tuning methods…

Large Language Models (LLMs) demonstrate remarkable translation capabilities in high-resource language tasks, yet their performance in low-resource languages is hindered by insufficient multilingual data during pre-training. To address…

Despite the steady progress in machine translation evaluation, existing automatic metrics struggle to capture how well meaning is preserved beyond sentence boundaries. We posit that reliance on a single intrinsic quality score, trained to…

We present the BME submission for the SIGMORPHON 2021 Task 0 Part 1, Generalization Across Typologically Diverse Languages shared task. We use an LSTM encoder-decoder model with three step training that is first trained on all languages,…

Foundation language models learn from their finetuning input context in different ways. In this paper, we reformulate inputs during finetuning for challenging translation tasks, leveraging model strengths from pretraining in novel ways to…

This paper presents EvolveMT for efficiently combining multiple machine translation (MT) engines. The proposed system selects the output from a single engine for each segment by utilizing online learning techniques to predict the most…

Multimodal Large Language Models (MLLMs) have achieved significant success in Speech-to-Text Translation (S2TT) tasks. While most existing research has focused on English-centric translation directions, the exploration of many-to-many…

Large language models (LLMs) have exhibited remarkable performance in various natural language processing tasks. Techniques like instruction tuning have effectively enhanced the proficiency of LLMs in the downstream task of machine…

This study investigates how Large Language Models (LLMs) leverage source and reference data in machine translation evaluation task, aiming to better understand the mechanisms behind their remarkable performance in this task. We design the…

The rapid proliferation of LLMs has created a critical evaluation paradox: while LLMs claim multilingual proficiency, comprehensive non-machine-translated benchmarks exist for fewer than 30 languages, leaving >98% of the world's 7,000…

Alignment with human preferences is an important step in developing accurate and safe large language models. This is no exception in machine translation (MT), where better handling of language nuances and context-specific variations leads…

We introduce TASER (Translation Assessment via Systematic Evaluation and Reasoning), a metric that uses Large Reasoning Models (LRMs) for automated translation quality assessment. TASER harnesses the explicit reasoning capabilities of LRMs…

Assessing the performance of interpreting services is a complex task, given the nuanced nature of spoken language translation, the strategies that interpreters apply, and the diverse expectations of users. The complexity of this task become…

Imposing constraints on machine translation systems presents a challenging issue because these systems are not trained to make use of constraints in generating adequate, fluent translations. In this paper, we leverage the capabilities of…

Automatic machine translation metrics typically rely on human translations to determine the quality of system translations. Common wisdom in the field dictates that the human references should be of very high quality. However, there are no…

Reasoning-oriented large language models (RLMs) achieve strong gains on tasks such as mathematics and coding by generating explicit intermediate reasoning. However, their impact on machine translation (MT) remains underexplored. We…

This report presents an automatic evaluation of the general machine translation task of the Seventh Conference on Machine Translation (WMT22). It evaluates a total of 185 systems for 21 translation directions including high-resource to…

Text-to-SQL systems enable users to interact with structured databases using natural language, eliminating the need for specialized programming knowledge. In this work, we introduce GEMMA-SQL, a lightweight and efficient text-to-SQL model…

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…

Insufficient modeling of human preferences within the reward model is a major obstacle for leveraging human feedback to improve translation quality. Fortunately, quality estimation (QE), which predicts the quality of a given translation…