Heroes, Villains, and Victims, and GPT-3: Automated Extraction of Character Roles Without Training Data

• URL: http://arxiv.org/abs/2205.07557v2
• Date: Tue, 17 May 2022 08:09:51 GMT
• Title: Heroes, Villains, and Victims, and GPT-3: Automated Extraction of Character Roles Without Training Data
• Authors: Dominik Stammbach, Maria Antoniak, Elliott Ash
• Abstract summary: GPT-3 can identify the hero, villain, and victim in diverse domains: newspaper articles, movie plot summaries, and political speeches. This paper shows how to use large-scale pre-trained language models to extract character roles from narrative texts without training data.
• Score: 4.718182951842264
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper shows how to use large-scale pre-trained language models to extract character roles from narrative texts without training data. Queried with a zero-shot question-answering prompt, GPT-3 can identify the hero, villain, and victim in diverse domains: newspaper articles, movie plot summaries, and political speeches.

Related papers

• From Panels to Prose: Generating Literary Narratives from Comics [55.544015596503726]
  We develop an automated system that generates text-based literary narratives from manga comics. Our approach aims to create an evocative and immersive prose that not only conveys the original narrative but also captures the depth and complexity of characters.
  arXiv  Detail & Related papers  (2025-03-30T07:18:10Z)
• MoCha: Towards Movie-Grade Talking Character Synthesis [62.007000023747445]
  We introduce Talking Characters, a more realistic task to generate talking character animations directly from speech and text. Unlike talking head, Talking Characters aims at generating the full portrait of one or more characters beyond the facial region. We propose MoCha, the first of its kind to generate talking characters.
  arXiv  Detail & Related papers  (2025-03-30T04:22:09Z)
• Entity Framing and Role Portrayal in the News [34.704721889186644]
  dataset includes 1,378 recent news articles in five languages (Bulgarian, English, Hindi, European Portuguese, and Russian) focusing on two critical domains of global significance: the Ukraine-Russia War and Climate Change. The dataset uses a unique taxonomy inspired by storytelling elements, comprising 22 fine-grained roles, or archetypes, nested within three main categories: protagonist, antagonist, and innocent.
  arXiv  Detail & Related papers  (2025-02-20T16:44:46Z)
• Show, Don't Tell: Uncovering Implicit Character Portrayal using LLMs [19.829683714192615]
  We introduce LIIPA, a framework for prompting large language models to uncover implicit character portrayals. We find that LIIPA outperforms existing approaches, and is more robust to increasing character counts. Our work demonstrates the potential benefits of using LLMs to analyze complex characters.
  arXiv  Detail & Related papers  (2024-12-05T19:46:53Z)
• Generating Visual Stories with Grounded and Coreferent Characters [63.07511918366848]
  We present the first model capable of predicting visual stories with consistently grounded and coreferent character mentions. Our model is finetuned on a new dataset which we build on top of the widely used VIST benchmark. We also propose new evaluation metrics to measure the richness of characters and coreference in stories.
  arXiv  Detail & Related papers  (2024-09-20T14:56:33Z)
• Are Large Language Models Capable of Generating Human-Level Narratives? [114.34140090869175]
  This paper investigates the capability of LLMs in storytelling, focusing on narrative development and plot progression. We introduce a novel computational framework to analyze narratives through three discourse-level aspects. We show that explicit integration of discourse features can enhance storytelling, as is demonstrated by over 40% improvement in neural storytelling.
  arXiv  Detail & Related papers  (2024-07-18T08:02:49Z)
• Improving Quotation Attribution with Fictional Character Embeddings [11.259583037191772]
  We propose to augment a popular quotation attribution system, BookNLP, with character embeddings that encode global stylistic information of characters. We show that combining BookNLP's contextual information with our proposed global character embeddings improves the identification of speakers for anaphoric and implicit quotes.
  arXiv  Detail & Related papers  (2024-06-17T09:46:35Z)
• CHIRON: Rich Character Representations in Long-Form Narratives [98.273323001781]
  We propose CHIRON, a new character sheet' based representation that organizes and filters textual information about characters. We validate CHIRON via the downstream task of masked-character prediction, where our experiments show CHIRON is better and more flexible than comparable summary-based baselines. metrics derived from CHIRON can be used to automatically infer character-centricity in stories, and that these metrics align with human judgments.
  arXiv  Detail & Related papers  (2024-06-14T17:23:57Z)
• Retrieval Enhanced Zero-Shot Video Captioning [69.96136689829778]
  We bridge video and text using three key models: a general video understanding model XCLIP, a general image understanding model CLIP, and a text generation model GPT-2. To address this problem, we propose using learnable tokens as a communication medium between frozen GPT-2 and frozen XCLIP. Experiments show 4% to 20% improvements in terms of the main metric CIDEr compared to the existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-05-11T16:22:00Z)
• Large Language Models Meet Harry Potter: A Bilingual Dataset for Aligning Dialogue Agents with Characters [70.84938803753062]
  We introduce the Harry Potter Dialogue dataset, designed to advance the study of dialogue agents and character alignment. The dataset encompasses all dialogue sessions (in both English and Chinese) from the Harry Potter series. It is annotated with vital background information, including dialogue scenes, speakers, character relationships, and attributes.
  arXiv  Detail & Related papers  (2022-11-13T10:16:39Z)
• MBTI Personality Prediction for Fictional Characters Using Movie Scripts [34.24896499537589]
  We construct a benchmark, Story2Personality, to predict a movie character's MBTI or Big 5 personality types. Experiments show that our task is challenging for the existing text classification models. We propose a multi-view model for personality prediction using both verbal and non-verbal descriptions.
  arXiv  Detail & Related papers  (2022-10-20T03:41:07Z)
• "Let Your Characters Tell Their Story": A Dataset for Character-Centric Narrative Understanding [31.803481510886378]
  We present LiSCU -- a new dataset of literary pieces and their summaries paired with descriptions of characters that appear in them. We also introduce two new tasks on LiSCU: Character Identification and Character Description Generation. Our experiments with several pre-trained language models adapted for these tasks demonstrate that there is a need for better models of narrative comprehension.
  arXiv  Detail & Related papers  (2021-09-12T06:12:55Z)
• PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking [128.76063992147016]
  We present PlotMachines, a neural narrative model that learns to transform an outline into a coherent story by tracking the dynamic plot states. In addition, we enrich PlotMachines with high-level discourse structure so that the model can learn different writing styles corresponding to different parts of the narrative.
  arXiv  Detail & Related papers  (2020-04-30T17:16:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.