HalOmi: A Manually Annotated Benchmark for Multilingual Hallucination and Omission Detection in Machine Translation

David Dale, Elena Voita, Janice Lam, Prangthip Hansanti, Christophe Ropers, Elahe Kalbassi, Cynthia Gao, Loic Barrault, Marta R. Costa-jussà

Submission Type: Regular Long Paper

Submission Track: Resources and Evaluation

Submission Track 2: Machine Translation

Keywords: Hallucination, Omissions, Dataset, Machine Translation

TL;DR: We release an annotated dataset for the hallucination and omission phenomena covering 18 translation directions with varying resource levels and scripts.

Abstract:

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.

Submission Number: 156