Search Results for author: Shenghui Li

Found 5 papers, 4 papers with code

Slot Self-Attentive Dialogue State Tracking

1 code implementation22 Jan 2021 Fanghua Ye, Jarana Manotumruksa, Qiang Zhang, Shenghui Li, Emine Yilmaz

Then a stacked slot self-attention is applied on these features to learn the correlations among slots.

Dialogue State Tracking Task-Oriented Dialogue Systems

Auto-weighted Robust Federated Learning with Corrupted Data Sources

1 code implementation14 Jan 2021 Shenghui Li, Edith Ngai, Fanghua Ye, Thiemo Voigt

In this paper, we address this challenge by proposing Auto-weighted Robust Federated Learning (arfl), a novel approach that jointly learns the global model and the weights of local updates to provide robustness against corrupted data sources.

Federated Learning Privacy Preserving

Enhancing Conversational Search: Large Language Model-Aided Informative Query Rewriting

1 code implementation15 Oct 2023 Fanghua Ye, Meng Fang, Shenghui Li, Emine Yilmaz

Furthermore, we propose distilling the rewriting capabilities of LLMs into smaller models to reduce rewriting latency.

Conversational Search Language Modelling +2

An Experimental Study of Byzantine-Robust Aggregation Schemes in Federated Learning

no code implementations14 Feb 2023 Shenghui Li, Edith C. -H. Ngai, Thiemo Voigt

In recent years, several robust aggregation schemes have been proposed to defend against malicious updates from Byzantine clients and improve the robustness of federated learning.

Federated Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.