Semi-Synthetic Parallel Data for Translation Quality Estimation: A Case Study of Dataset Building for an Under-Resourced Language Pair

Quality estimation (QE) plays a crucial role in machine translation (MT) workflows, as it serves to evaluate generated outputs that have no reference translations and to determine whether human post-editing or full retranslation is necessary. Yet, developing highly accurate, adaptable and reliable QE systems for under-resourced language pairs remains largely unsolved, due mainly to limited parallel corpora and to diverse language-dependent factors, such as with morphosyntactically complex languages. This study presents a semi-synthetic parallel dataset for English-to-Hebrew QE, generated by creating English sentences based on examples of usage that illustrate typical linguistic patterns, translating them to Hebrew using multiple MT engines, and filtering outputs via BLEU-based selection. Each translated segment was manually evaluated and scored by a linguist, and we also incorporated professionally translated English-Hebrew segments from our own resources, which were assigned the highest quality score. Controlled translation errors were introduced to address linguistic challenges, particularly regarding gender and number agreement, and we trained neural QE models, including BERT and XLM-R, on this dataset to assess sentence-level MT quality. Our findings highlight the impact of dataset size, distributed balance, and error distribution on model performance. We will describe the challenges, methodology and results of our experiments, and specify future directions aimed at improving QE performance. This research contributes to advancing QE models for under resourced language pairs, including morphology-rich languages.

MTQE.en-he: Machine Translation Quality Estimation for English-Hebrew

We release MTQE.en-he: to our knowledge, the first publicly available English-Hebrew benchmark for Machine Translation Quality Estimation. MTQE.en-he contains 959 English segments from WMT24++, each paired with a machine translation into Hebrew, and Direct Assessment scores of the translation quality annotated by three human experts. We benchmark ChatGPT prompting, TransQuest, and CometKiwi and show that ensembling the three models outperforms the best single model (CometKiwi) by 6.4 percentage points Pearson and 5.6 percentage points Spearman. Fine-tuning experiments with TransQuest and CometKiwi reveal that full-model updates are sensitive to overfitting and distribution collapse, yet parameter-efficient methods (LoRA, BitFit, and FTHead, i.e., fine-tuning only the classification head) train stably and yield improvements of 2-3 percentage points. MTQE.en-he and our experimental results enable future research on this under-resourced language pair.