@inproceedings{koksal-etal-2024-silveralign,
    title = "{S}ilver{A}lign: {MT}-Based Silver Data Algorithm for Evaluating Word Alignment",
    author = {Koksal, Abdullatif  and
      Severini, Silvia  and
      Sch{\"u}tze, Hinrich},
    editor = "Calzolari, Nicoletta  and
      Kan, Min-Yen  and
      Hoste, Veronique  and
      Lenci, Alessandro  and
      Sakti, Sakriani  and
      Xue, Nianwen",
    booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
    month = may,
    year = "2024",
    address = "Torino, Italia",
    publisher = "ELRA and ICCL",
    url = "https://preview.aclanthology.org/ingest-emnlp/2024.lrec-main.1290/",
    pages = "14812--14825",
    abstract = "Word alignments are essential for a variety of NLP tasks. Therefore, choosing the best approaches for their creation is crucial. However, the scarce availability of gold evaluation data makes the choice difficult. We propose SilverAlign, a new method to automatically create silver data for the evaluation of word aligners by exploiting machine translation and minimal pairs. We show that performance on our silver data correlates well with gold benchmarks for 9 language pairs, making our approach a valid resource for evaluation of different languages and domains when gold data is not available. This addresses the important scenario of missing gold data alignments for low-resource languages."
}