Improving Automatic Quotation Attribution in Literary Novels
This addresses the challenge of in-the-wild inference for literary analysis, but it is incremental as it builds on existing sub-task approaches without a major breakthrough.
The paper tackled quotation attribution in literary novels by breaking it into four sub-tasks and benchmarking state-of-the-art models, showing that a simple sequential model achieves accuracy on par with existing methods.
Current models for quotation attribution in literary novels assume varying levels of available information in their training and test data, which poses a challenge for in-the-wild inference. Here, we approach quotation attribution as a set of four interconnected sub-tasks: character identification, coreference resolution, quotation identification, and speaker attribution. We benchmark state-of-the-art models on each of these sub-tasks independently, using a large dataset of annotated coreferences and quotations in literary novels (the Project Dialogism Novel Corpus). We also train and evaluate models for the speaker attribution task in particular, showing that a simple sequential prediction model achieves accuracy scores on par with state-of-the-art models.