Dialogue Utterance
Dialogue utterance research focuses on understanding and modeling the complexities of conversational exchanges, aiming to improve human-computer interaction and AI capabilities. Current research emphasizes developing models that accurately capture nuances like personality, emotion, and uncertainty in dialogue, often leveraging large language models (LLMs) and contrastive learning techniques for improved performance. This work is significant for advancing AI's ability to engage in natural, contextually aware conversations, with applications ranging from improved chatbots and virtual assistants to more effective tools for healthcare and education.
Papers
CADS: A Systematic Literature Review on the Challenges of Abstractive Dialogue Summarization
Frederic Kirstein, Jan Philip Wahle, Bela Gipp, Terry Ruas
Fine-tuning with HED-IT: The impact of human post-editing for dialogical language models
Daniela Occhipinti, Michele Marchi, Irene Mondella, Huiyuan Lai, Felice Dell'Orletta, Malvina Nissim, Marco Guerini