ACL Findings2022
Learning and Evaluating Character Representations in Novels
Naoya Inoue, Charuta Pethe, Allen Kim, Steven Skiena
摘要
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.
问 Lune
几分钟读透这篇 Paper,不用再花一下午。
Lune 能读完全文,也能读引用它的顶会 Paper,讲清它的结论、证据和局限,每一点都注明出自哪篇 Paper。不用硬啃,也不靠猜。
已有 4 篇顶会 Paper 引用了它。别等审稿人问起,先弄清它们发现了什么。
脉络
- Detecting and Grounding Important Characters in Visual Stories 引用了 "Let Your Characters Tell Their Story": A Dataset for Character-Centric Narrative Understanding
- Multi-level Contrastive Learning for Script-based Character Understanding 引用了 "Let Your Characters Tell Their Story": A Dataset for Character-Centric Narrative Understanding
- AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts 引用了 Information-Theoretic Probing with Minimum Description Length
- Evaluating Taxonomy Free Character Role Labeling (TF-CRL) in News Stories using Large Language Models 引用了 "Let Your Characters Tell Their Story": A Dataset for Character-Centric Narrative Understanding
引用它的顶会 Paper4
- Detecting and Grounding Important Characters in Visual StoriesDanyang Liu, Frank KellerAAAI 2023 · 11 次引用
- Major Entity Identification: A Generalizable Alternative to Coreference ResolutionKawshik Sundar, Shubham Toshniwal, Makarand Tapaswi, Vineet GandhiEMNLP 2024 · 4 次引用
- Multi-level Contrastive Learning for Script-based Character UnderstandingDawei Li, Hengyuan Zhang, Yanran Li, Shiping YangEMNLP 2023 · 2 次引用
- Evaluating Taxonomy Free Character Role Labeling (TF-CRL) in News Stories using Large Language ModelsDavid G. Hobson, Derek Ruths, Andrew PiperEMNLP 2025
它引用的 Paper10
- AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated PromptsTaylor Shin, Yasaman Razeghi, Robert L. Logan IV, Eric Wallace 等EMNLP 2020 · 1,162 次引用
- Interpreting Pretrained Contextualized Representations via Reductions to Static EmbeddingsRishi Bommasani, Kelly Davis, Claire CardieACL 2020 · 137 次引用
- Information-Theoretic Probing with Minimum Description LengthElena Voita, Ivan TitovEMNLP 2020 · 34 次引用
- "Let Your Characters Tell Their Story": A Dataset for Character-Centric Narrative UnderstandingFaeze Brahman, Meng Huang, Oyvind Tafjord, Chao Zhao 等EMNLP Findings 2021 · 20 次引用
- Chapter Captor: Text Segmentation in NovelsCharuta Pethe, Allen Kim, Steven SkienaEMNLP 2020 · 18 次引用
相关 Paper
- BookWorm: A Dataset for Character Description and AnalysisArgyrios Papoudakis, Mirella Lapata, Frank KellerEMNLP Findings 2024 · 1 次引用
- 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 次引用
- Using Graph Representation Learning with Schema Encoders to Measure the Severity of Depressive SymptomsSimin Hong, Anthony G. Cohn, David Crossland HoggICLR 2022 · 16 次引用
- Contrastive Document Representation Learning with Graph Attention NetworksPeng Xu, Xinchi Chen, Xiaofei Ma, Zhiheng Huang 等EMNLP Findings 2021 · 10 次引用
- Improving Quotation Attribution with Fictional Character EmbeddingsGaspard Michel, Elena V. Epure, Romain Hennequin, Christophe CerisaraEMNLP Findings 2024 · 3 次引用
