The Elephant in the Coreference Room: Resolving Coreference in Full-Length French Fiction Works

2025-10-17

AI Summary

Current computational literary studies are hindered by the scarcity of annotated long-form literary texts—particularly those exhibiting complex coreference chains—making robust evaluation of coreference resolution models difficult. To address this, we introduce the first coreference resolution corpus built over complete French novels, comprising full-length original texts of three works, thereby overcoming the long-document data bottleneck. We propose a modular processing pipeline that integrates contextualized representation learning with explicit referential chain modeling, specifically designed for long-distance and multi-hop coreference. Our method achieves strong performance on lengthy documents, enables fine-grained error analysis, and successfully generalizes to downstream literary NLP tasks—including fictional character gender inference—demonstrating both practical utility and scalability in computational literary analysis.

Technology Category

• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning

Application Category

• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

While coreference resolution is attracting more interest than ever from computational literature researchers, representative datasets of fully annotated long documents remain surprisingly scarce. In this paper, we introduce a new annotated corpus of three full-length French novels, totaling over 285,000 tokens. Unlike previous datasets focused on shorter texts, our corpus addresses the challenges posed by long, complex literary works, enabling evaluation of coreference models in the context of long reference chains. We present a modular coreference resolution pipeline that allows for fine-grained error analysis. We show that our approach is competitive and scales effectively to long documents. Finally, we demonstrate its usefulness to infer the gender of fictional characters, showcasing its relevance for both literary analysis and downstream NLP tasks.

Problem

• Addressing coreference resolution challenges in lengthy French novels
• Providing annotated corpus for evaluating long reference chains
• Developing scalable pipeline for literary analysis and gender inference

Innovation

• Annotated corpus of three full-length French novels
• Modular coreference resolution pipeline for analysis
• Scales effectively to long documents with chains