@inproceedings{zhang-etal-2023-lexical,
    title = "Lexical Translation Inconsistency-Aware Document-Level Translation Repair",
    author = "Zhang, Zhen  and
      Li, Junhui  and
      Tao, Shimin  and
      Yang, Hao",
    editor = "Rogers, Anna  and
      Boyd-Graber, Jordan  and
      Okazaki, Naoaki",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.findings-acl.791/",
    doi = "10.18653/v1/2023.findings-acl.791",
    pages = "12492--12505",
    abstract = "Following the idea of ``one translation per discourse'', in this paper we aim to improve translation consistency via document-level translation repair (DocRepair), i.e., automatic post-editing on translations of documents. To this end, we propose a lexical translation inconsistency-aware DocRepair to explicitly model translation inconsistency. First we locate the inconsistency in automatic translation. Then we provide translation candidates for those inconsistency. Finally, we propose lattice-like input to properly model inconsistent tokens and phrases and their candidates. Experimental results on three document-level translation datasets show that based on G-Transformer, a state-of-the-art document-to-document (Doc2Doc) translation model, our Doc2Doc DocRepair achieves significant improvement on translation quality in BLEU scores, but also greatly improves lexical translation consistency."
}