@inproceedings{chang-etal-2026-makes,
    title = "What Makes an Ideal Quote? Recommending ``Unexpected yet Rational'' Quotations via Novelty",
    author = "Chang, Powei  and
      Xiao, Jin  and
      Yue, Guanglei  and
      He, Qianyu  and
      Xiao, Yanghua  and
      Yang, Deqing  and
      Liang, Jiaqing",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.362/",
    pages = "7985--8017",
    ISBN = "979-8-89176-390-6",
    abstract = "Quotation recommendation enriches writing by suggesting quotations that fit a given context, but prior systems largely focus on topical relevance and overlook what makes quotes memorable. Based on a user study, we find that preferred quotations are often unexpected yet rational, motivating the goal of selecting quotes that are contextually novel while semantically coherent. We propose NovelQR, which (1) uses a generative label agent to map quotations and contexts into multi-dimensional deep-meaning labels for label-enhanced retrieval, and (2) reranks candidates with a token-level novelty estimator that mitigates auto-regressive continuation bias. Experiments on bilingual datasets across diverse domains show that NovelQR is preferred by human judges and improves overall recommendation quality over strong baselines, while achieving competitive novelty estimation."
}