Mennatallah El-Assady is an Assistant Professor in the Department of Computer Science at ETH Zürich, where she leads the Interactive Visualization and Intelligence Augmentation (IVIA) lab. Prior to this, she was a postdoctoral research fellow at the ETH AI Center and held research associate positions in Germany and Canada. Her doctoral research on human-AI collaboration garnered the prestigious joint dissertation award from the German, Austrian, and Swiss Informatics Societies, as well as an honorable mention for the VGTC VIS Doctoral Dissertation Award. Her interdisciplinary work spans data analysis, visualization, computational linguistics, and explainable artificial intelligence, with a primary focus on the design of interactive human-AI collaboration interfaces that enhance problem-solving and decision-making. She is particularly passionate about empowering individuals by fostering co-adaptive processes between humans and AI agents. With years of experience collaborating closely with political science and linguistics scholars, El-Assady led the creation of the LingVis.io platform. She is currently focused on creating a novel human-AI communication framework (human-ai.io). Additionally, she is a co-founder and co-organizer of several influential workshop series, including Vis4DH and VISxAI. In recognition of her pioneering contributions, El-Assady was named a Eurographics Junior Fellow in 2023. Her groundbreaking work at the intersection of visualization and machine learning has also earned her the 2024 IEEE VIS Significant New Researcher Award and the 2023 EuroVis Early Career Award.
Verbatim text transcripts capture the rapid exchange of opinions, arguments, and information among participants of a conversation. As a form of communication that is based on social interaction, multiparty conversations are characterized by an incremental development of their content structure. In contrast to highly-edited text data (e.g., literary, scientific, and technical publications), verbatim text transcripts contain non-standard lexical items and syntactic patterns. Thus, analyzing these transcripts automatically introduces multiple challenges.