@inproceedings{zetsu-etal-2022-lexically,
    title = "Lexically Constrained Decoding with Edit Operation Prediction for Controllable Text Simplification",
    author = "Zetsu, Tatsuya  and
      Kajiwara, Tomoyuki  and
      Arase, Yuki",
    editor = "{\v{S}}tajner, Sanja  and
      Saggion, Horacio  and
      Ferr{\'e}s, Daniel  and
      Shardlow, Matthew  and
      Sheang, Kim Cheng  and
      North, Kai  and
      Zampieri, Marcos  and
      Xu, Wei",
    booktitle = "Proceedings of the Workshop on Text Simplification, Accessibility, and Readability (TSAR-2022)",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates (Virtual)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.tsar-1.13/",
    doi = "10.18653/v1/2022.tsar-1.13",
    pages = "147--153",
    abstract = "Controllable text simplification assists language learners by automatically rewriting complex sentences into simpler forms of a target level. However, existing methods tend to perform conservative edits that keep complex words intact. To address this problem, we employ lexically constrained decoding to encourage rewriting. Specifically, the proposed method predicts edit operations conditioned to a target level and creates positive/negative constraints for words that should/should not appear in an output sentence. The experimental results confirm that our method significantly outperforms previous methods and demonstrates a new state-of-the-art performance."
}