Dr. Kun Lu will attend the 38th Annual Association for the Advancement of Artificial Intelligence (AAAI) Conference on Artificial Intelligence in February 2024 in Vancouver, Canada.
Dr. Lu co-authored a research paper titled "Dependency Structure-Enhanced Graph Attention Networks for Event Detection." Event detection is an essential and challenging task of information extraction. Its target is to identify events and their types from text, including information about "Who did What to Whom and Where and When." The work proposed a dependency structure-enhanced event detection framework. The enhanced dependency structure allows the embedding representations of dependency relations to be updated as nodes rather than edges in a graph neural network. Extensive experiments are conducted to validate the effectiveness of the method, and the results confirm its superiority over the state-of-the-art base-lines.
The AAAI conference is a highly regarded conference on Artificial Intelligence and is competitive, with an acceptance rate of 23.75% this year.
