Related papers: QE-EBM: Using Quality Estimators as Energy Loss fo…

Neural Machine Translation (NMT) is a new approach for Machine Translation (MT), and due to its success, it has absorbed the attention of many researchers in the field. In this paper, we study NMT model on Persian-English language pairs, to…

Multilingual understanding models (or encoder-based), pre-trained via masked language modeling, have achieved promising results on many language understanding tasks (e.g., mBERT). However, these non-autoregressive (NAR) models still…

The effectiveness of Neural Machine Translation (NMT) models largely depends on the vocabulary used at training; small vocabularies can lead to out-of-vocabulary problems -- large ones, to memory issues. Subword (SW) tokenization has been…

Decoding strategies largely determine the quality of Large Language Model (LLM) outputs, yet widely used heuristics such as greedy or fixed temperature/top-p decoding are static and often task-agnostic, leading to suboptimal or inconsistent…

The advent of Multilingual Language Models (MLLMs) and Large Language Models has spawned innovation in many areas of natural language processing. Despite the exciting potential of this technology, its impact on developing high-quality…

Common intermediate language representation in neural machine translation can be used to extend bilingual to multilingual systems by incremental training. In this paper, we propose a new architecture based on introducing an interlingual…

Neural machine translation (NMT) is often criticized for failures that happen without awareness. The lack of competency awareness makes NMT untrustworthy. This is in sharp contrast to human translators who give feedback or conduct further…

From both human translators (HT) and machine translation (MT) researchers' point of view, translation quality evaluation (TQE) is an essential task. Translation service providers (TSPs) have to deliver large volumes of translations which…

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…

Quantum error correction is widely thought to be the key to fault-tolerant quantum computation. However, determining the most suited encoding for unknown error channels or specific laboratory setups is highly challenging. Here, we present a…

Reinforcement learning (RL) has been widely used in training large language models (LLMs) for preventing unexpected outputs, eg reducing harmfulness and errors. However, existing RL methods mostly adopt the instance-level reward, which is…

In reinforcement learning, an agent interacts sequentially with an environment to maximize a reward, receiving only partial, probabilistic feedback. This creates a fundamental exploration-exploitation trade-off: the agent must explore to…

The computational cost of training multimodal large language models (MLLMs) grows rapidly with the number of processed tokens. Existing efficiency methods mainly target inference via token reduction or merging, offering limited benefits…

Neural machine translation (NMT) models are conventionally trained with token-level negative log-likelihood (NLL), which does not guarantee that the generated translations will be optimized for a selected sequence-level evaluation metric.…

Energy-based models (EBMs) exhibit a variety of desirable properties in predictive tasks, such as generality, simplicity and compositionality. However, training EBMs on high-dimensional datasets remains unstable and expensive. In this…

We leverage embedding duplication between aligned sub-words to extend the Parent-Child transfer learning method, so as to improve low-resource machine translation. We conduct experiments on benchmark datasets of My-En, Id-En and Tr-En…

The fine-tuning of pre-trained large language models (LLMs) using reinforcement learning (RL) is generally formulated as direct policy optimization. This approach was naturally favored as it efficiently improves a pretrained LLM, seen as an…

Current evaluation benchmarks for question answering (QA) in Indic languages often rely on machine translation of existing English datasets. This approach suffers from bias and inaccuracies inherent in machine translation, leading to…

As language model (LM) agents become increasingly capable and adopted in real-world applications, there is a growing need for scalable evaluation frameworks beyond costly, manually designed benchmarks. We propose information-theoretic…

Good quality monolingual word embeddings (MWEs) can be built for languages which have large amounts of unlabeled text. MWEs can be aligned to bilingual spaces using only a few thousand word translation pairs. For low resource languages…