1 code implementation • 5 Sep 2024 • Jie Ma, Zhitao Gao, Qi Chai, Wangchun Sun, Pinghui Wang, Hongbin Pei, Jing Tao, Lingyun Song, Jun Liu, Chen Zhang, Lizhen Cui
Furthermore, the integration experiments with various LLMs on the mentioned datasets highlight the flexibility of DoG.
1 code implementation • 18 Aug 2024 • Nuo Xu, Pinghui Wang, Junzhou Zhao, Feiyang Sun, Lin Lan, Jing Tao, Li Pan, Xiaohong Guan
On the other hand, D-LADAN presents a novel momentum-updated memory mechanism to dynamically sense the posterior similarity between law articles (or charges) and a weighted GDO to adaptively capture the distinctions for revising the inductive bias caused by the data imbalance problem.
1 code implementation • 18 Apr 2024 • Jie Ma, Min Hu, Pinghui Wang, Wangchun Sun, Lingyun Song, Hongbin Pei, Jun Liu, Youtian Du
The former leads to a large, diverse test space, while the latter results in a comprehensive robustness evaluation on rare, frequent, and overall questions.
Audio-visual Question Answering
Audio-Visual Question Answering (AVQA)
+3
1 code implementation • 11 Apr 2024 • Tao Duan, Junzhou Zhao, Shuo Zhang, Jing Tao, Pinghui Wang
To address this problem, we propose a novel method, i. e., Key-Value sequence Early Co-classification (KVEC), which leverages both inner- and inter-correlations of items in a tangled key-value sequence through key correlation and value correlation to learn a better sequence representation.
no code implementations • 21 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.
1 code implementation • 25 May 2023 • Zi Liang, Pinghui Wang, Ruofei Zhang, Nuo Xu, Lifeng Xing, Shuo Zhang
The drastic increase in language models' parameters has led to a new trend of deploying models in cloud servers, raising growing concerns about private inference for Transformer-based models.
Ranked #1 on
Multi-task Language Understanding
on MMLU (5-Shot)
(using extra training data)
1 code implementation • 25 May 2023 • Zi Liang, Pinghui Wang, Ruofei Zhang, Shuo Zhang, Xiaofan Ye Yi Huang, Junlan Feng
Recent years have seen increasing concerns about the unsafe response generation of large-scale dialogue systems, where agents will learn offensive or biased behaviors from the real-world corpus.
1 code implementation • 6 May 2023 • Jie Ma, Pinghui Wang, Zewei Wang, Dechen Kong, Min Hu, Ting Han, Jun Liu
Question answering methods are well-known for leveraging data bias, such as the language prior in visual question answering and the position bias in machine reading comprehension (extractive question answering).
Extractive Question-Answering
Machine Reading Comprehension
+2
no code implementations • 27 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.
no code implementations • 10 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.
no code implementations • 26 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.
1 code implementation • 25 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.
1 code implementation • 15 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.
1 code implementation • 25 Nov 2020 • Jie Ma, Qi Chai, Jun Liu, Qingyu Yin, Pinghui Wang, Qinghua Zheng
Textbook Question Answering (TQA) is a task that one should answer a diagram/non-diagram question given a large multi-modal context consisting of abundant essays and diagrams.
1 code implementation • NeurIPS 2020 • Lin Lan, Pinghui Wang, Xuefeng Du, Kaikai Song, Jing Tao, Xiaohong Guan
We study the problem of node classification on graphs with few-shot novel labels, which has two distinctive properties: (1) There are novel labels to emerge in the graph; (2) The novel labels have only a few representative nodes for training a classifier.
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.
no code implementations • 2 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.
2 code implementations • 23 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.
2 code implementations • 16 May 2019 • Lin Lan, Zhenguo Li, Xiaohong Guan, Pinghui Wang
Despite significant progress, deep reinforcement learning (RL) suffers from data-inefficiency and limited generalization.