Can GPT models Follow Human Summarization Guidelines? Evaluating ChatGPT and GPT-4 for Dialogue Summarization

no code implementations • 25 Oct 2023 • Yongxin Zhou, Fabien Ringeval, François Portet

This study explores the capabilities of prompt-driven Large Language Models (LLMs) like ChatGPT and GPT-4 in adhering to human guidelines for dialogue summarization.

Semantic Similarity Semantic Textual Similarity

Evaluating Emotional Nuances in Dialogue Summarization

no code implementations • 23 Jul 2023 • Yongxin Zhou, Fabien Ringeval, François Portet

Automatic dialogue summarization is a well-established task that aims to identify the most important content from human conversations to create a short textual summary.

Effectiveness of French Language Models on Abstractive Dialogue Summarization Task

no code implementations • LREC 2022 • Yongxin Zhou, François Portet, Fabien Ringeval

We further discuss the limits of such pre-trained models and the challenges that must be addressed for summarizing spontaneous dialogues.

Abstractive Dialogue Summarization