Summary of Bookworm: a Dataset For Character Description and Analysis, by Argyrios Papoudakis et al.
BookWorm: A Dataset for Character Description and Analysis
by Argyrios Papoudakis, Mirella Lapata, Frank Keller
First submitted to arxiv on: 14 Oct 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Information Retrieval (cs.IR); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The study investigates the comprehension of characters in full-length books, focusing on complex narratives with numerous interacting characters. The authors define two tasks: character description, generating a factual profile, and character analysis, offering an in-depth interpretation. They introduce the BookWorm dataset, pairing books from the Gutenberg Project with human-written descriptions and analyses. Using this dataset, they evaluate state-of-the-art long-context models in zero-shot and fine-tuning settings, utilizing retrieval-based and hierarchical processing for book-length inputs. The findings show that retrieval-based approaches outperform hierarchical ones in both tasks, while fine-tuned models using coreference-based retrieval produce the most factual descriptions. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The study looks at how well computers can understand characters in long books with many storylines. They want to know what makes a good character description and analysis. To do this, they created a special dataset with books from the Gutenberg Project and people’s written descriptions and analyses of the characters. Then, they tested top computer models that can handle long texts. They found that some models are better at describing characters than others and that some ways of training the models work better than others. |
Keywords
» Artificial intelligence » Coreference » Fine tuning » Zero shot
