GraphLit: Learning Text-Enriched Dynamic Character Network Representations for Literary Study
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Self-Supervised LearningSimilar Papers 제목 키워드 기반
Embed More Ignore Less (EMIL): Exploiting Enriched Representations for Arabic NLP
Our research focuses on the potential improvements of exploiting language specific characteristics in the form of embeddings by neural networks. More specifically, we investigate the capability of neural techniques and e…
named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NER+3Enriching the E2E dataset
This study introduces an enriched version of the E2E dataset, one of the most popular language resources for data-to-text NLG. We extract intermediate representations for popular pipeline tasks such as discourse ordering…
Referring ExpressionReferring expression generationPhonetic-enriched Text Representation for Chinese Sentiment Analysis with Reinforcement Learning
The Chinese pronunciation system offers two characteristics that distinguish it from other languages: deep phonemic orthography and intonation variations. We are the first to argue that these two important properties can…
Chinese Sentiment Analysisreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1Feature-Enriched Character-Level Convolutions for Text Regression
Learning Accurate and Enriched Features for Stereo Image Super-Resolution
Stereo image super-resolution (stereoSR) aims to enhance the quality of super-resolution results by incorporating complementary information from an alternative view. Although current methods have shown significant advanc…
Image Super-ResolutionStereo Image Super-ResolutionSuper-Resolution