Lune

ACL Findings2022

Learning and Evaluating Character Representations in Novels

Naoya Inoue, Charuta Pethe, Allen Kim, Steven Skiena

Abstract

We address the problem of learning fixedlength vector representations of characters in novels. Recent advances in word embeddings have proven successful in learning entity representations from short texts, but fall short on longer documents because they do not capture full book-level information. To overcome the weakness of such text-based embeddings, we propose two novel methods for representing characters: (i) graph neural network-based embeddings from a full corpus-based character network; and (ii) low-dimensional embeddings constructed from the occurrence pattern of characters in each novel. We test the quality of these character embeddings using a new benchmark suite to evaluate character representations, encompassing 12 different tasks. We show that our representation techniques combined with text-based embeddings lead to the best character representations, outperforming text-based embeddings in four tasks. Our dataset is made publicly available to stimulate additional work in this area.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

4 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Detecting and Grounding Important Characters in Visual Stories cites "Let Your Characters Tell Their Story": A Dataset for Character-Centric Narrative Understanding
  • Multi-level Contrastive Learning for Script-based Character Understanding cites "Let Your Characters Tell Their Story": A Dataset for Character-Centric Narrative Understanding
  • AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts cites Information-Theoretic Probing with Minimum Description Length
  • Evaluating Taxonomy Free Character Role Labeling (TF-CRL) in News Stories using Large Language Models cites "Let Your Characters Tell Their Story": A Dataset for Character-Centric Narrative Understanding
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers4

  1. Detecting and Grounding Important Characters in Visual StoriesDanyang Liu, Frank KellerAAAI 2023 · 11 citations
  2. Major Entity Identification: A Generalizable Alternative to Coreference ResolutionKawshik Sundar, Shubham Toshniwal, Makarand Tapaswi, Vineet GandhiEMNLP 2024 · 4 citations
  3. Multi-level Contrastive Learning for Script-based Character UnderstandingDawei Li, Hengyuan Zhang, Yanran Li, Shiping YangEMNLP 2023 · 2 citations
  4. Evaluating Taxonomy Free Character Role Labeling (TF-CRL) in News Stories using Large Language ModelsDavid G. Hobson, Derek Ruths, Andrew PiperEMNLP 2025

Builds on10

  1. AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated PromptsTaylor Shin, Yasaman Razeghi, Robert L. Logan IV, Eric Wallace et al.EMNLP 2020 · 1,162 citations
  2. Interpreting Pretrained Contextualized Representations via Reductions to Static EmbeddingsRishi Bommasani, Kelly Davis, Claire CardieACL 2020 · 137 citations
  3. Information-Theoretic Probing with Minimum Description LengthElena Voita, Ivan TitovEMNLP 2020 · 34 citations
  4. "Let Your Characters Tell Their Story": A Dataset for Character-Centric Narrative UnderstandingFaeze Brahman, Meng Huang, Oyvind Tafjord, Chao Zhao et al.EMNLP Findings 2021 · 20 citations
  5. Chapter Captor: Text Segmentation in NovelsCharuta Pethe, Allen Kim, Steven SkienaEMNLP 2020 · 18 citations

Related papers

  1. BookWorm: A Dataset for Character Description and AnalysisArgyrios Papoudakis, Mirella Lapata, Frank KellerEMNLP Findings 2024 · 1 citation
  2. Connecting the Dots: What Graph-Based Text Representations Work Best for Text Classification using Graph Neural Networks?Margarita Bugueño, Gerard de MeloEMNLP Findings 2023 · 8 citations
  3. Using Graph Representation Learning with Schema Encoders to Measure the Severity of Depressive SymptomsSimin Hong, Anthony G. Cohn, David Crossland HoggICLR 2022 · 16 citations
  4. Contrastive Document Representation Learning with Graph Attention NetworksPeng Xu, Xinchi Chen, Xiaofei Ma, Zhiheng Huang et al.EMNLP Findings 2021 · 10 citations
  5. Improving Quotation Attribution with Fictional Character EmbeddingsGaspard Michel, Elena V. Epure, Romain Hennequin, Christophe CerisaraEMNLP Findings 2024 · 3 citations
Dusk over the sea between two cliffs drawn in fine vertical lines