New method improves quotation attribution accuracy in literature

Researchers have developed a new method for attributing quotations to speakers in literary texts, addressing a long-standing challenge in computational linguistics. This novel approach, termed 'joint scoring,' utilizes an encoder-based formulation to efficiently process multiple attributions within a large context window. It achieves state-of-the-art accuracy on the Project Dialogism Novel Corpus, outperforming previous methods in both speed and precision. AI

IMPACT This research could enhance literary analysis tools by enabling more accurate and efficient identification of dialogue sources within texts.

RANK_REASON The item is a research paper detailing a new method for quotation attribution in literary texts. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

• A100
• arXiv
• BookNLP
• English
• ModernBookNLP
• Project Dialogism Novel Corpus

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →