DSpace Collection:
http://hdl.handle.net/10722/132157
2024-03-29T12:28:07ZGraphix-T5: Mixing Pre-trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing
http://hdl.handle.net/10722/341727
Title: Graphix-T5: Mixing Pre-trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing
Authors: Li, Jinyang; Hui, Binyuan; Cheng, Reynold; Qin, Bowen; Ma, Chenhao; Huo, Nan; Huang, Fei; Du, Wenyu; Si, Luo; Li, Yongbin
Abstract: <p>The task of text-to-SQL parsing, which aims at converting natural language questions into executable SQL queries, has garnered increasing attention in recent years. One of the major challenges in text-to-SQL parsing is domain generalization, i.e., how to generalize well to unseen databases. Recently, the pre-trained text-to-text transformer model, namely T5, though not specialized for text-to-SQL parsing, has achieved state-of-the-art performance on standard benchmarks targeting domain generalization. In this work, we explore ways to further augment the pre-trained T5 model with specialized components for text-to-SQL parsing. Such components are expected to introduce structural inductive bias into text-to-SQL parsers thus improving the model’s capacity on (potentially multi-hop) reasoning, which is critical for generating structure-rich SQLs. To this end, we propose a new architecture GRAPHIX-T5, a mixed model with the standard pre-trained transformer model augmented by specially-designed graph-aware layers. Extensive experiments and analysis demonstrate the effectiveness of GRAPHIX-T5 across four text-to-SQL benchmarks: SPIDER, SYN, REALISTIC and DK. GRAPHIX-T5 surpasses all other T5-based parsers with a significant margin, achieving new state-of-the-art performance. Notably, GRAPHIX-T5-large reaches performance superior to the original T5-large by 5.7% on exact match (EM) accuracy and 6.6% on execution accuracy (EX). This even outperforms the T5-3B by 1.2% on EM and 1.5% on EX</p>2023-06-26T00:00:00ZA Simple Wideband Slot Antenna
http://hdl.handle.net/10722/340725
Title: A Simple Wideband Slot Antenna
Authors: Zhou, C F; Wong, Hang; Yeung, Kwan L2018-04-01T00:00:00ZA Horizontally Polarized Omnidirectional Antenna Array with Side-Lobe Suppression
http://hdl.handle.net/10722/340724
Title: A Horizontally Polarized Omnidirectional Antenna Array with Side-Lobe Suppression
Authors: Wang, Bo; Wong, Bo Hang; Xiao, Bing; Yeung, Lawrence Kwan
Abstract: <p>A broadband horizontal polarized omnidirectional antenna array with low side-lobe is presented. The proposed array consists of four wideband omnidirectional antenna elements and an uneven power divider. The antenna element consists of four pairs of arc dipole and a balun. Simultaneously, the slots placed at the edge of the arc dipole further broaden the impendence bandwidth. With PSO (particle swarm optimization) optimizing the different amplitudes of each element and element spacing, the side-lobe suppression is obtained. The simulation results show that the proposed antenna element and antenna array can achieve a bandwidth of 1.68-2.37 GHz and 1.72-2.37 GHz (S11<-10dB), respectively. With an omnidirectional radiation pattern in H- plane and a low side-lobe of -19dB in E-plane, the antenna array has peak gains ranging from 5.75 to 7.2 dBi.</p>2019-03-03T00:00:00ZRouting in Black Box: Modularized Load Balancing for Multipath Data Center Networks
http://hdl.handle.net/10722/340722
Title: Routing in Black Box: Modularized Load Balancing for Multipath Data Center Networks
Authors: Fan, Fujie; Hu, Bing; Yeung, Lawrence Kwan
Abstract: <p>Multipath networks are widely used in data centers and load balancing is one of the most important technologies to improve their performances. Due to the ever-increasing in data center network size, existing load balancing algorithms face the challenges of efficiency and scalability. In this paper, we propose a new load balancing algorithm for large-scale, multi-tier fat-tree based data center networks. Different from the conventional architectures, a multi-tier fat-tree is divided into multiple routing domains according to the topology, and the routing processes in different domains are independent. The devices outside a routing domain can only access the specific interfaces provided by this domain. It is thus very convenient for deployment and modular upgrade. We also design a distributed and data-driven feedback mechanism, with which the routing decision is based on the global load information. We prove that the new algorithm can achieve perfect load balancing in multipath networks and show that the new algorithm outperforms all other load balancing algorithms in performance.</p>2019-04-29T00:00:00Z