Search Results for author: Junzhou Zhao

Found 11 papers, 4 papers with code

Robust Visual Question Answering: Datasets, Methods, and Future Challenges

no code implementations21 Jul 2023 Jie Ma, Pinghui Wang, Dechen Kong, Zewei Wang, Jun Liu, Hongbin Pei, Junzhou Zhao

Specifically, we first provide an overview of the development process of datasets from in-distribution and out-of-distribution perspectives.

Question Answering Visual Question Answering

Multi-Action Dialog Policy Learning from Logged User Feedback

no code implementations27 Feb 2023 Shuo Zhang, Junzhou Zhao, Pinghui Wang, Tianxiang Wang, Zi Liang, Jing Tao, Yi Huang, Junlan Feng

To cope with this problem, we explore to improve multi-action dialog policy learning with explicit and implicit turn-level user feedback received for historical predictions (i. e., logged user feedback) that are cost-efficient to collect and faithful to real-world scenarios.

Fast Gumbel-Max Sketch and its Applications

no code implementations10 Feb 2023 Yuanming Zhang, Pinghui Wang, Yiyan Qi, Kuankuan Cheng, Junzhou Zhao, Guangjian Tian, Xiaohong Guan

The well-known Gumbel-Max Trick for sampling elements from a categorical distribution (or more generally a non-negative vector) and its variants have been widely used in areas such as machine learning and information retrieval.

Information Retrieval Retrieval

Federated Learning over Coupled Graphs

no code implementations26 Jan 2023 Runze Lei, Pinghui Wang, Junzhou Zhao, Lin Lan, Jing Tao, Chao Deng, Junlan Feng, Xidian Wang, Xiaohong Guan

In this work, we propose a novel FL framework for graph data, FedCog, to efficiently handle coupled graphs that are a kind of distributed graph data, but widely exist in a variety of real-world applications such as mobile carriers' communication networks and banks' transaction networks.

Federated Learning Node Classification

"Think Before You Speak": Improving Multi-Action Dialog Policy by Planning Single-Action Dialogs

1 code implementation25 Apr 2022 Shuo Zhang, Junzhou Zhao, Pinghui Wang, Yu Li, Yi Huang, Junlan Feng

Multi-action dialog policy (MADP), which generates multiple atomic dialog actions per turn, has been widely applied in task-oriented dialog systems to provide expressive and efficient system responses.

Multi-Task Learning

Learning to Check Contract Inconsistencies

1 code implementation15 Dec 2020 Shuo Zhang, Junzhou Zhao, Pinghui Wang, Nuo Xu, Yang Yang, Yiting Liu, Yi Huang, Junlan Feng

This will result in the issue of contract inconsistencies, which may severely impair the legal validity of the contract.

Distinguish Confusing Law Articles for Legal Judgment Prediction

1 code implementation ACL 2020 Nuo Xu, Pinghui Wang, Long Chen, Li Pan, Xiaoyan Wang, Junzhou Zhao

Legal Judgment Prediction (LJP) is the task of automatically predicting a law case's judgment results given a text describing its facts, which has excellent prospects in judicial assistance systems and convenient services for the public.

Fast Generating A Large Number of Gumbel-Max Variables

no code implementations2 Feb 2020 Yiyan Qi, Pinghui Wang, Yuanming Zhang, Junzhou Zhao, Guangjian Tian, Xiaohong Guan

Instead of computing $k$ independent Gumbel random variables directly, we find that there exists a technique to generate these variables in descending order.

Graph Embedding Information Retrieval +1

MR-GNN: Multi-Resolution and Dual Graph Neural Network for Predicting Structured Entity Interactions

2 code implementations23 May 2019 Nuo Xu, Pinghui Wang, Long Chen, Jing Tao, Junzhou Zhao

To resolve these problems, we present MR-GNN, an end-to-end graph neural network with the following features: i) it uses a multi-resolution based architecture to extract node features from different neighborhoods of each node, and, ii) it uses dual graph-state long short-term memory networks (L-STMs) to summarize local features of each graph and extracts the interaction features between pairwise graphs.

On Analyzing Estimation Errors due to Constrained Connections in Online Review Systems

no code implementations14 Jul 2013 Junzhou Zhao

Constrained connection is the phenomenon that a reviewer can only review a subset of products/services due to narrow range of interests or limited attention capacity.

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