Conversational Data
Conversational data analysis focuses on extracting meaningful insights from human-computer and human-human interactions, aiming to improve various applications like chatbots, recommender systems, and educational tools. Current research emphasizes developing methods for analyzing complex conversational structures, including identifying topics, emotions, and intents, often leveraging large language models (LLMs) and advanced techniques like graph-based methods and attention mechanisms to process and interpret this data. This field is crucial for advancing human-computer interaction, enabling the development of more effective and personalized AI systems, and providing valuable insights into human communication patterns across diverse contexts.
Papers
Book2Dial: Generating Teacher-Student Interactions from Textbooks for Cost-Effective Development of Educational Chatbots
Junling Wang, Jakub Macina, Nico Daheim, Sankalan Pal Chowdhury, Mrinmaya Sachan
MAGID: An Automated Pipeline for Generating Synthetic Multi-modal Datasets
Hossein Aboutalebi, Hwanjun Song, Yusheng Xie, Arshit Gupta, Justin Sun, Hang Su, Igor Shalyminov, Nikolaos Pappas, Siffi Singh, Saab Mansour