Papers by Gaspard Michel

4 papers
Improving Quotation Attribution with Fictional Character Embeddings (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent methods to attribute quotes to human logic lack character representations, which often leads to errors in more challenging examples of attribution: anaphoric and implicit quotes.
Approach: They propose to augment a popular quotation attribution system, BookNLP, with character embeddings that encode global stylistic information of characters derived from an off-the-shelf stylometric model, Universal Authorship Representation (UAR).
Outcome: The proposed system improves anaphoric and implicit quotes, reaching state-of-the-art.
Computational Narrative Understanding for Expressive Text-to-Speech (2026.findings-acl)

Copied to clipboard

Challenge: Recent advances in text-to-speech systems have been driven by large, multi-domain speech corpora.
Approach: They propose a large-scale 5.3K hours of expressive speech drawn from character quotations . they fine-tune a flow-matching model and train from scratch .
Outcome: The proposed model improves expressivity and intelligibility while training from scratch improves expressiveness of an autoregressive model.
Evaluating LLMs for Quotation Attribution in Literary Texts: A Case Study of LLaMa3 (2025.naacl-short)

Copied to clipboard

Challenge: Large Language Models (LLMs) have shown promising results in literary tasks . however, quotation attribution remains a challenging task and methods that generalize across writing styles are lacking analysis regarding book memorization and annotation contamination.
Approach: They evaluate the ability of Llama-3 to attribute utterances of direct-speech to their speaker in novels by assessing the impact of book memorization and annotation contamination.
Outcome: The proposed model outperforms existing models on a corpus of 28 novels and shows that book memorization and annotation contamination do not explain the performance gain.
Automatic Annotation of Direct Speech in Written French Narratives (2023.acl-long)

Copied to clipboard

Challenge: a new framework for AADS annotation in written text is needed for literary studies.
Approach: They propose to use automatic annotation of direct speech (AADS) in written text to compare works by different authors . they adapted a large-to-date French narrative dataset annotated with DS per word .
Outcome: The proposed framework is a step further to encourage more research on the topic.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations