EMNLP Findings2024
Improving Quotation Attribution with Fictional Character Embeddings
Gaspard Michel, Elena V. Epure, Romain Hennequin, Christophe Cerisara
Abstract
Humans naturally attribute utterances of direct speech to their speaker in literary works. When attributing quotes, we process contextual information but also access mental representations of characters that we build and revise throughout the narrative. Recent methods to automatically attribute such utterances have explored simulating human logic with deterministic rules or learning new implicit rules with neural networks when processing contextual information. However, these systems inherently lack character representations, which often leads to errors in more challenging examples of attribution: anaphoric and implicit quotes. In this work, we propose to augment a popular quotation attribution system, BookNLP, with character embeddings that encode global stylistic information of characters derived from an off-theshelf stylometric model, Universal Authorship Representation (UAR). We create DramaCV 1 , a corpus of English drama plays from the 15th to 20th century that we automatically annotate for Authorship Verification of fictional characters utterances, and release two versions of UAR trained on DramaCV, that are tailored for literary characters analysis. Then, through an extensive evaluation on 28 novels, we show that combining BookNLP's contextual information with our proposed global character embeddings improves the identification of speakers for anaphoric and implicit quotes, reaching state-of-the-art performance.
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.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Multi-level Contrastive Learning for Script-based Character Understanding cites Learning and Evaluating Character Representations in Novels
- Multi-level Contrastive Learning for Script-based Character Understanding cites "Let Your Characters Tell Their Story": A Dataset for Character-Centric Narrative Understanding
- Learning and Evaluating Character Representations in Novels cites "Let Your Characters Tell Their Story": A Dataset for Character-Centric Narrative Understanding
Cited by top-tier papers1
Builds on8
- Supervised Contrastive LearningPrannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna et al.NeurIPS 2020 · 7,049 citations
- SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational AbilitiesDong Zhang, Shimin Li, Xin Zhang, Jun Zhan et al.EMNLP Findings 2023 · 189 citations
- "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
- Learning and Evaluating Character Representations in NovelsNaoya Inoue, Charuta Pethe, Allen Kim, Steven SkienaACL Findings 2022 · 5 citations
- Multi-level Contrastive Learning for Script-based Character UnderstandingDawei Li, Hengyuan Zhang, Yanran Li, Shiping YangEMNLP 2023 · 2 citations
Related papers
- What does the sea say to the shore? A BERT based DST style approach for speaker to dialogue attribution in novelsCarolina Cuesta-Lázaro, Animesh Prasad, Trevor WoodACL 2022
- SIG: Speaker Identification in Literature via Prompt-Based GenerationZhenlin Su, Liyan Xu, Jin Xu, Jiangnan Li et al.AAAI 2024
- Learning Interpretable Style Embeddings via Prompting LLMsAjay Patel, Delip Rao, Ansh Kothary, Kathleen R. McKeown et al.EMNLP Findings 2023 · 10 citations
- Idiosyncratic but not Arbitrary: Learning Idiolects in Online Registers Reveals Distinctive yet Consistent Individual StylesJian Zhu, David JurgensEMNLP 2021 · 16 citations
- Measuring Information Propagation in Literary Social NetworksMatthew Sims, David BammanEMNLP 2020 · 2 citations
