Hallucinations in machine translation are translations that contain information completely unrelated to the input. Omissions are translations that do not include some of the input information. While both cases tend to be catastrophic errors undermining user trust, annotated data with these types of pathologies is extremely scarce and is limited to a few high-resource languages. In this work, we release an annotated dataset for the hallucination and omission phenomena covering 18 translation directions with varying resource levels and scripts. Our annotation covers different levels of partial and full hallucinations as well as omissions both at the sentence and at the word level. Additionally, we revisit previous methods for hallucination and omission detection, show that conclusions made based on a single language pair largely do not hold for a large-scale evaluation, and establish new solid baselines.

翻译：机器翻译中的幻觉指译文中包含与输入完全无关的信息，漏译则指译文未包含部分输入信息。这两种情况通常会导致灾难性错误，损害用户对翻译系统的信任，但标注此类病态现象的语料极为稀缺，且仅局限于少数高资源语言。本研究发布了一个涵盖资源水平和文字系统各异的18个翻译方向的幻觉与漏译现象标注数据集。我们的标注覆盖了句子级和词级的不同程度的部分幻觉、完全幻觉以及漏译现象。此外，我们重新审视了此前针对幻觉与漏译的检测方法，证明基于单一语言对得出的结论在大规模评估中基本不成立，并为后续研究建立了新的可靠基线。