相关论文: Evaluating Extremely Low-Resource Machine Translat…

For machine translation, a vast majority of language pairs in the world are considered low-resource because they have little parallel data available. Besides the technical challenges of learning with limited supervision, it is difficult to…

Standard automatic metrics, e.g. BLEU, are not reliable for document-level MT evaluation. They can neither distinguish document-level improvements in translation quality from sentence-level ones, nor identify the discourse phenomena that…

This study examines whether Low-Rank Adaptation (LoRA) fine-tuned Large Language Models (LLMs) can approximate the performance of fully fine-tuned models in generating human-interpretable decisions and explanations for malware…

Analysing translation quality in regards to specific linguistic phenomena has historically been difficult and time-consuming. Neural machine translation has the attractive property that it can produce scores for arbitrary translations, and…

Multilingual NMT has become an attractive solution for MT deployment in production. But to match bilingual quality, it comes at the cost of larger and slower models. In this work, we consider several ways to make multilingual NMT faster at…

Accurate translation of bug reports is critical for efficient collaboration in global software development. In this study, we conduct the first comprehensive evaluation of machine translation (MT) performance on bug reports, analyzing the…

Unlike classical lexical overlap metrics such as BLEU, most current evaluation metrics (such as BERTScore or MoverScore) are based on black-box language models such as BERT or XLM-R. They often achieve strong correlations with human…

Reproducible benchmarks are crucial in driving progress of machine translation research. However, existing machine translation benchmarks have been mostly limited to high-resource or well-represented languages. Despite an increasing…

Neural Machine translation is a challenging task due to the inherent complex nature and the fluidity that natural languages bring. Nonetheless, in recent years, it has achieved state-of-the-art performance in several language pairs.…

Machine Translation (MT) plays a pivotal role in cross-lingual information access, public policy communication, and equitable knowledge dissemination. However, critical meaning errors, such as factual distortions, intent reversals, or…

Quality estimation (QE) is the task of automatically evaluating the quality of translations without human-translated references. Calculating BLEU between the input sentence and round-trip translation (RTT) was once considered as a metric…

Large Language Models (LLMs) have significantly advanced Machine Translation (MT), applying them to linguistically complex domains-such as Social Network Services, literature etc. In these scenarios, translations often require handling…

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…

Perfect machine translation (MT) would render cross-lingual transfer (XLT) by means of multilingual language models (mLMs) superfluous. Given, on the one hand, the large body of work on improving XLT with mLMs and, on the other hand, recent…

Multilingual machine translation models often outperform traditional bilingual models by leveraging translation knowledge transfer. Recent advancements have led to these models supporting hundreds of languages and achieving state-of-the-art…

Despite significant improvements in enhancing the quality of translation, context-aware machine translation (MT) models underperform in many cases. One of the main reasons is that they fail to utilize the correct features from context when…

Reinforcement learning from human feedback (RLHF) is a recent technique to improve the quality of the text generated by a language model, making it closer to what humans would generate. A core ingredient in RLHF's success in aligning and…

Structured prediction tasks, like machine translation, involve learning functions that map structured inputs to structured outputs. Recurrent Neural Networks (RNNs) have historically been a popular choice for such tasks, including in…

Machine Translation (MT) is widely employed to address resource scarcity in low-resource languages by generating synthetic data from high-resource counterparts. While sentiment preservation in translation has long been studied, a critical…

Unsupervised translation has reached impressive performance on resource-rich language pairs such as English-French and English-German. However, early studies have shown that in more realistic settings involving low-resource, rare languages,…