What Makes an Ideal Quote? Recommending "Unexpected yet Rational" Quotations via Novelty
- URL: http://arxiv.org/abs/2602.22220v1
- Date: Mon, 15 Dec 2025 12:19:37 GMT
- Title: What Makes an Ideal Quote? Recommending "Unexpected yet Rational" Quotations via Novelty
- Authors: Bowei Zhang, Jin Xiao, Guanglei Yue, Qianyu He, Yanghua Xiao, Deqing Yang, Jiaqing Liang,
- Abstract summary: We formalize quote recommendation as choosing contextually novel but semantically coherent quotations.<n>A generative label agent first interprets each quotation and its surrounding context into multi-dimensional deep-meaning labels.<n>A token-level novelty estimator then reranks candidates while mitigating auto-regressive continuation bias.
- Score: 66.51974095399409
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Quotation recommendation aims to enrich writing by suggesting quotes that complement a given context, yet existing systems mostly optimize surface-level topical relevance and ignore the deeper semantic and aesthetic properties that make quotations memorable. We start from two empirical observations. First, a systematic user study shows that people consistently prefer quotations that are ``unexpected yet rational'' in context, identifying novelty as a key desideratum. Second, we find that strong existing models struggle to fully understand the deep meanings of quotations. Inspired by defamiliarization theory, we therefore formalize quote recommendation as choosing contextually novel but semantically coherent quotations. We operationalize this objective with NovelQR, a novelty-driven quotation recommendation framework. A generative label agent first interprets each quotation and its surrounding context into multi-dimensional deep-meaning labels, enabling label-enhanced retrieval. A token-level novelty estimator then reranks candidates while mitigating auto-regressive continuation bias. Experiments on bilingual datasets spanning diverse real-world domains show that our system recommends quotations that human judges rate as more appropriate, more novel, and more engaging than other baselines, while matching or surpassing existing methods in novelty estimation.
Related papers
- SCIRGC: Multi-Granularity Citation Recommendation and Citation Sentence Preference Alignment [2.0383262889621867]
We propose the SciRGC framework, which aims to automatically recommend citation articles and generate citation sentences for citation locations within articles.<n>The framework addresses two key challenges in academic citation generation: 1) how to accurately identify the author's citation intent and find relevant citation papers, and 2) how to generate high-quality citation sentences that align with human preferences.
arXiv Detail & Related papers (2025-05-26T15:09:10Z) - RA-MTR: A Retrieval Augmented Multi-Task Reader based Approach for Inspirational Quote Extraction from Long Documents [5.436122513215347]
We propose a novel context-based quote extraction system that aims to extract the most relevant quote from a long text.<n>We formulate this quote extraction as an open domain question answering problem first by employing a vector-store based retriever.<n>We introduce a novel multi-task framework RA-MTR that improves the state-of-the-art performance, achieving a maximum improvement of 5.08% in BoW F1-score.
arXiv Detail & Related papers (2025-02-17T18:46:46Z) - RankCSE: Unsupervised Sentence Representations Learning via Learning to
Rank [54.854714257687334]
We propose a novel approach, RankCSE, for unsupervised sentence representation learning.
It incorporates ranking consistency and ranking distillation with contrastive learning into a unified framework.
An extensive set of experiments are conducted on both semantic textual similarity (STS) and transfer (TR) tasks.
arXiv Detail & Related papers (2023-05-26T08:27:07Z) - SciMON: Scientific Inspiration Machines Optimized for Novelty [68.46036589035539]
We explore and enhance the ability of neural language models to generate novel scientific directions grounded in literature.
We take a dramatic departure with a novel setting in which models use as input background contexts.
We present SciMON, a modeling framework that uses retrieval of "inspirations" from past scientific papers.
arXiv Detail & Related papers (2023-05-23T17:12:08Z) - QuoteR: A Benchmark of Quote Recommendation for Writing [80.83859760380616]
We build a large and fully open quote recommendation dataset called QuoteR.
We conduct an extensive evaluation of existing quote recommendation methods on QuoteR.
We propose a new quote recommendation model that significantly outperforms previous methods on all three parts of QuoteR.
arXiv Detail & Related papers (2022-02-26T14:01:44Z) - Towards generating citation sentences for multiple references with
intent control [86.53829532976303]
We build a novel generation model with the Fusion-in-Decoder approach to cope with multiple long inputs.
Experiments demonstrate that the proposed approaches provide much more comprehensive features for generating citation sentences.
arXiv Detail & Related papers (2021-12-02T15:32:24Z) - Quotation Recommendation and Interpretation Based on Transformation from
Queries to Quotations [17.011179660418538]
We introduce a transformation matrix that directly maps the query representations to quotation representations.
Experiments on two datasets in English and Chinese show that our model outperforms previous state-of-the-art models.
arXiv Detail & Related papers (2021-05-29T07:25:59Z) - Learning Neural Textual Representations for Citation Recommendation [7.227232362460348]
We propose a novel approach to citation recommendation using a deep sequential representation of the documents (Sentence-BERT) cascaded with Siamese and triplet networks in a submodular scoring function.
To the best of our knowledge, this is the first approach to combine deep representations and submodular selection for a task of citation recommendation.
arXiv Detail & Related papers (2020-07-08T12:38:50Z) - Context-Based Quotation Recommendation [60.93257124507105]
We propose a novel context-aware quote recommendation system.
It generates a ranked list of quotable paragraphs and spans of tokens from a given source document.
We conduct experiments on a collection of speech transcripts and associated news articles.
arXiv Detail & Related papers (2020-05-17T17:49:53Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.