School of Engineering Department of Computer Science and Engineering 123 Reasoning with Large Foundation Models Supervisor: SONG Yangqiu / CSE Student: WU Yuetong / DSCT ZHOU Yukai / MATH-PMA Course: UROP 1100, Spring UROP 1100, Spring DialAM-2024 is a complicated dialogue argument mining task based on the Inference Anchoring Theory (IAT) framework which makes possible to obtain homogeneous annotations of dialogue argumentation from speech and argumentation and allowing a more complete analysis of argumentation in dialogues. DialAM2024 consists of two sub-tasks: the identification of propositional (argumentative) relations, and the identification of illocutionary (speech act) relations. In this paper, we proposed our system for both subtasks. Depending on the text classification essence of the of the task, our proposed system first aggregate a human-defined prompt with given text to form a training set. Pre-trained models are then finetuned on the aggregated training set to generate the predictions. Our submitted maps achieved a good score in the evaluation and achieved a second place on ILO-General level. Our codes and pre-trained models are available at https://github.com/Arwenwutietie/DialAM-2024 for future contributions. Efficient Queries Over Database Supervisor: WONG Raymond Chi Wing / CSE Student: CHEUNG Alan Pak To / COMP Course: UROP 1100, Summer The popularity of recommendation systems is steadily increasing, with various types being widely employed in E-commerce and video websites. Many companies, such as Amazon or Netflix, utilize these systems to predict user actions and provide personalized recommendations. By employing session-based recommendation with graph neural networks, the intricate transitions between items can be more effectively captured, leading to more precise recommendations for the users. This UROP project aims to comprehensively study the fundamental concepts of recommendation systems while understanding the principles behind different algorithms and data filtering methods. Additionally, we will develop tools that optimize computational efficiency during training. Efficient Queries Over Database Supervisor: WONG Raymond Chi Wing / CSE Student: DONG Yunao / DSCT Course: UROP 1100, Summer This summer semester, though not beginning my research yet, I started to learn course COMP3711 Design and Analysis of Algorithms. Through weeks of studying, I ’ve gained abundant knowledge and insight of algorithms.
RkJQdWJsaXNoZXIy NDk5Njg=