Fast and Accurate Quotation Attribution in Literary Texts

2026-08-03

AI Summary

This work addresses the longstanding challenge in literary text analysis of balancing accuracy and efficiency in quotation attribution. The authors propose an efficient joint scoring approach based on a pretrained encoder, leveraging large-context window modeling and a joint inference strategy to simultaneously resolve multiple quotation attributions while preserving long-range coreference information. Evaluated on the PDNC dataset, the method achieves 94.5% accuracy, offering a 20-fold speedup over conventional approaches and surpassing large language model–based solutions by more than three orders of magnitude in inference speed. The accompanying ModernBookNLP toolkit is released as open-source software to facilitate further research in computational literary analysis.

Abstract

Attributing quotations to their speakers in literary texts remains an open challenge. Standard methods, which independently predict a speaker mention for each quotation, are efficient but still limited in accuracy. In contrast, large language model (LLM) approaches achieve strong performance, but their computational cost limits their use in large-scale literary analysis. We propose an encoder-based efficient formulation that resolves multiple quotation attributions within a shared, large context window. Using our new formulation, \textit{joint scoring}, we report state-of-the-art (SOTA) performance on the Project Dialogism Novel Corpus (PDNC), comprising more than 35,000 manually annotated quotations from 22 English novels. Our best model reaches 94.5\% overall attribution accuracy while processing novels $20\times$ faster than comparable standard methods and more than $1000\times$ faster than LLM-based approaches on an A100 GPU. An analysis of models' representations suggests that joint scoring improves on challenging attribution examples by preserving long-range anaphora resolution signal, an information that we found already present in pretrained encoders. To facilitate adoption, we release ModernBookNLP, a modified fork of BookNLP that replaces its quotation attribution model with our best system available at https://github.com/gasmichel/ModernBookNLP_QA/.

Problem

• quotation attribution
• literary texts
• speaker identification
• anaphora resolution
• natural language processing

Innovation

• joint scoring
• quotation attribution
• efficient encoder
• long-range anaphora resolution
• literary text analysis