diff --git a/_posts/2026-05-28-EMNLP-gmichel.md b/_posts/2026-05-28-EMNLP-gmichel.md new file mode 100644 index 0000000..a8e3ead --- /dev/null +++ b/_posts/2026-05-28-EMNLP-gmichel.md @@ -0,0 +1,29 @@ +--- +layout: post +title: "GraphLit: Learning Text-Enriched Dynamic Character Network Representations for Literary Study" +date: 2026-05-28 10:00:00 +0200 +category: Publication +author: gmichel +readtime: 1 +domains: + - NLP +people: + - gmichel + - eepure + - rhennequin +publication_type: conference +publication_title: "GraphLit: Learning Text-Enriched Dynamic Character Network Representations for Literary Study" +publication_year: 2026 +publication_authors: Gaspard Michel, Elena V. Epure, Romain Hennequin, Christophe Cerisara, Mirella Lapata +publication_conference: EMNLP 2026 +publication_code: "https://github.com/gasmichel/GraphLit" +publication_preprint: "https://arxiv.org/pdf/2605.28643" +--- + +Methods to represent literary texts as graphs or sequences of graphs mainly focus on representing character interactions, and often overlook another crucial aspect: the textual context in which characters interact. +We introduce Dynamic Heterogeneous Character Networks (DHCNs), which organize long novels into temporally localized heterogeneous graphs that align +characters with their textual contexts. +We extract around 20,000 DHCNs from Project Gutenberg, and propose GraphLit, a self-supervised learning framework that learns rich literary representations through a masked graph autoencoder objective. +Across a wide range of 12 character-related tasks, GraphLit improves over text-only, graph-only and prior hybrid baselines. +Ablations over different kinds of dynamic graph structures and architectural elements show that grounding characters in their context is the main performance driver, while explicitly encoding narrative order and character relationships provide task-dependent improvements. +Finally, we demonstrate the applicability of DHCNs and GraphLit for literary analysis by studying the link between narrative non-linearity and dynamic social features. \ No newline at end of file diff --git a/_posts/2026-05-28-PrePrint-gmichel.md b/_posts/2026-05-28-PrePrint-gmichel.md deleted file mode 100644 index 20e3b6f..0000000 --- a/_posts/2026-05-28-PrePrint-gmichel.md +++ /dev/null @@ -1,23 +0,0 @@ ---- -layout: post -title: "GraphLit: Learning Text-Enriched Dynamic Character Network Representations for Literary Study" -date: 2026-05-28 10:00:00 +0200 -category: Publication -author: gmichel -readtime: 1 -domains: - - NLP -people: - - gmichel - - eepure - - rhennequin -publication_type: conference -publication_title: "GraphLit: Learning Text-Enriched Dynamic Character Network Representations for Literary Study" -publication_year: 2026 -publication_authors: Gaspard Michel, Elena V. Epure, Romain Hennequin, Christophe Cerisara, Mirella Lapata -publication_conference: Preprint -publication_code: "https://github.com/gasmichel/GraphLit" -publication_preprint: "https://arxiv.org/pdf/2605.28643" ---- - -Methods to represent literary texts as graphs or sequences of graphs mainly focus on representing character interactions, and often overlook another crucial aspect: the textual context in which characters interact. We introduce Dynamic Heterogeneous Character Networks (DHCNs), which organize long novels into temporally localized heterogeneous graphs that align characters with their textual contexts. We extract around 20,000 DHCNs from Project Gutenberg, and propose GraphLit, a self-supervised learning framework that learns rich literary representations through a masked graph autoencoder objective. Across a wide-range of 12 character-related tasks, GraphLit improves over text-only and graph-only baselines, particularly on tasks requiring contextual understanding. Finally, we demonstrate the applicability of DHCNs and GraphLit for literary analysis by studying the link between narrative non-linearity and dynamic social features. \ No newline at end of file diff --git a/_posts/2026-07-28-PrePrint-gmichel.md b/_posts/2026-07-28-PrePrint-gmichel.md new file mode 100644 index 0000000..8dbf151 --- /dev/null +++ b/_posts/2026-07-28-PrePrint-gmichel.md @@ -0,0 +1,26 @@ +--- +layout: post +title: "Fast and Accurate Quotation Attribution in Literary Texts" +date: 2026-08-03 10:00:00 +0200 +category: Publication +author: gmichel +readtime: 1 +domains: + - NLP +people: + - gmichel + - eepure +publication_type: conference +publication_title: "Fast and Accurate Quotation Attribution in Literary Texts" +publication_year: 2026 +publication_authors: Gaspard Michel, Hugo Attali, Elena V. Epure +publication_conference: Preprint +publication_code: "https://github.com/gasmichel/ModernBookNLP_QA/" +publication_preprint: "https://arxiv.org/pdf/2608.02359" +--- + +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, *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 [this link](https://github.com/gasmichel/ModernBookNLP_QA/). \ No newline at end of file