# Fast and Accurate Quotation Attribution in Literary Texts

arXiv: https://arxiv.org/abs/2608.02359 · HTML: https://mlsanity.com/paper/2608.02359/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 38 references that are in the map.
- First posted on arXiv 3 Aug 2026.

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [SpanBERT: Improving Pre-training by Representing and Predicting Spans](https://mlsanity.com/paper/1907.10529/) (2019)
- [How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings](https://mlsanity.com/paper/1909.00512/) (2019)
- [Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference](https://mlsanity.com/paper/2412.13663/) (2024)
- [Entity, Relation, and Event Extraction with Contextualized Span Representations](https://mlsanity.com/paper/1909.03546/) (2019)
- [Representation Degeneration Problem in Training Natural Language Generation Models](https://mlsanity.com/paper/1907.12009/) (2019)
- [End-to-end Neural Coreference Resolution](https://mlsanity.com/paper/1707.07045/) (2017)
- [DocRED: A Large-Scale Document-Level Relation Extraction Dataset](https://mlsanity.com/paper/1906.06127/) (2019)
- [Higher-order Coreference Resolution with Coarse-to-fine Inference](https://mlsanity.com/paper/1804.05392/) (2018)
- [A General Framework for Information Extraction using Dynamic Span Graphs](https://mlsanity.com/paper/1904.03296/) (2019)
- [An Annotated Dataset of Coreference in English Literature](https://mlsanity.com/paper/1912.01140/) (2019)
- [Coreference Resolution without Span Representations](https://mlsanity.com/paper/2101.00434/) (2021)
- [Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling](https://mlsanity.com/paper/1805.04787/) (2018)
- [Measuring Information Propagation in Literary Social Networks](https://mlsanity.com/paper/2004.13980/) (2020)
- [The Project Dialogism Novel Corpus: A Dataset for Quotation Attribution in Literary Texts](https://mlsanity.com/paper/2204.05836/) (2022)
- [The Emotion Dynamics of Literary Novels](https://mlsanity.com/paper/2403.02474/) (2024)
- [Improving Automatic Quotation Attribution in Literary Novels](https://mlsanity.com/paper/2307.03734/) (2023)
- [Evaluating LLMs for Quotation Attribution in Literary Texts: A Case Study of LLaMa3](https://mlsanity.com/paper/2406.11380/) (2024)
- [SIG: Speaker Identification in Literature via Prompt-Based Generation](https://mlsanity.com/paper/2312.14590/) (2023)
- [Distinguishing Fictional Voices: a Study of Authorship Verification Models for Quotation Attribution](https://mlsanity.com/paper/2401.16968/) (2024)
- [Improving Quotation Attribution with Fictional Character Embeddings](https://mlsanity.com/paper/2406.11368/) (2024)
- [GraphLit: Learning Text-Enriched Dynamic Character Network Representations for Literary Study](https://mlsanity.com/paper/2605.28643/) (2026)

## Abstract (arXiv)

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, textitjoint 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× faster than comparable standard methods and more than 1000× 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/ModernBookNLPQA/.