- admin
- 0 Comments
- 897 Views
Abstract:
Modern conversational models, epitomized by platforms such as ChatGPT, have showcased impressive strides in contextual comprehension and response formulation. Their ability to mimic human-like interaction is both fascinating and testament to advancements in the field. However, a noteworthy limitation observed across this landscape is their predominantly reactive nature. The essence of proactiveness—embodied by initiating dialogues, transitioning across topics, and presenting contextualized suggestions—is notably absent. This seminar will begin by charting the evolutionary trajectory of conversational AI. We will subsequently delve into a curated set of contemporary research endeavors aimed at cultivating proactive capabilities in conversational agents. Join us in exploring the next paradigm shift in conversational AI.
About our speaker:
Dr. Lizi Liao (Singapore Management University, Singapore) Dr. Lizi Liao is assistant professor of Computer Science at Singapore Management University, leading the CoAgent group. She obtained her Ph.D. from National University of Singapore in 2019. Her research interests center on conversational models, proactive conversational agents, and multimodal conversational search and recommendation as the application target. She publishes regularly in top AI and Data Science conferences and journals such as ACL, SIGIR, ACM MM, TKDE etc. One of her work was nominated in the ACM MM Best Paper Final List in 2018. She actively serves as organizing committee member of these prestigious conferences such as ACM MM 2019, NLPCC 2022, WSDM 2023 and WWW 2024, while chairs sessions at KDD 2021 and SIGIR 2022. She was recognized as the 2022 AI 2000 Most Influential Scholar Honorable Mention in Information Retrieval and Recommendation.
