Search Results for author: Weiwei Sun

Found 77 papers, 27 papers with code

Comparing Knowledge-Intensive and Data-Intensive Models for English Resource Semantic Parsing

no code implementations CL (ACL) 2021 Junjie Cao, Zi Lin, Weiwei Sun, Xiaojun Wan

Abstract In this work, we present a phenomenon-oriented comparative analysis of the two dominant approaches in English Resource Semantic (ERS) parsing: classic, knowledge-intensive and neural, data-intensive models.

Semantic Parsing

3D Gaussian Splatting as Markov Chain Monte Carlo

no code implementations15 Apr 2024 Shakiba Kheradmand, Daniel Rebain, Gopal Sharma, Weiwei Sun, Jeff Tseng, Hossam Isack, Abhishek Kar, Andrea Tagliasacchi, Kwang Moo Yi

While 3D Gaussian Splatting has recently become popular for neural rendering, current methods rely on carefully engineered cloning and splitting strategies for placing Gaussians, which does not always generalize and may lead to poor-quality renderings.

Neural Rendering

Enhanced Generative Recommendation via Content and Collaboration Integration

no code implementations27 Mar 2024 Yidan Wang, Zhaochun Ren, Weiwei Sun, Jiyuan Yang, Zhixiang Liang, Xin Chen, Ruobing Xie, Su Yan, Xu Zhang, Pengjie Ren, Zhumin Chen, Xin Xin

However, existing generative recommendation approaches still encounter challenges in (i) effectively integrating user-item collaborative signals and item content information within a unified generative framework, and (ii) executing an efficient alignment between content information and collaborative signals.

Collaborative Filtering Language Modelling +1

Improving the Robustness of Large Language Models via Consistency Alignment

no code implementations21 Mar 2024 Yukun Zhao, Lingyong Yan, Weiwei Sun, Guoliang Xing, Shuaiqiang Wang, Chong Meng, Zhicong Cheng, Zhaochun Ren, Dawei Yin

The training process is accomplished by self-rewards inferred from the trained model at the first stage without referring to external human preference resources.

Instruction Following Response Generation

How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study

1 code implementation25 Feb 2024 Tianjie Ju, Weiwei Sun, Wei Du, Xinwei Yuan, Zhaochun Ren, Gongshen Liu

Previous work has showcased the intriguing capability of large language models (LLMs) in retrieving facts and processing context knowledge.

ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling

1 code implementation NeurIPS 2023 Yuqi Chen, Kan Ren, Yansen Wang, Yuchen Fang, Weiwei Sun, Dongsheng Li

A wide range of experiments on both synthetic and real-world datasets have illustrated the superior modeling capacities and prediction performance of ContiFormer on irregular time series data.

Inductive Bias Irregular Time Series +1

Densify Your Labels: Unsupervised Clustering with Bipartite Matching for Weakly Supervised Point Cloud Segmentation

no code implementations11 Dec 2023 Shaobo Xia, Jun Yue, Kacper Kania, Leyuan Fang, Andrea Tagliasacchi, Kwang Moo Yi, Weiwei Sun

We propose a weakly supervised semantic segmentation method for point clouds that predicts "per-point" labels from just "whole-scene" annotations while achieving the performance of recent fully supervised approaches.

Clustering Point Cloud Segmentation +3

PointNeRF++: A multi-scale, point-based Neural Radiance Field

no code implementations4 Dec 2023 Weiwei Sun, Eduard Trulls, Yang-Che Tseng, Sneha Sambandam, Gopal Sharma, Andrea Tagliasacchi, Kwang Moo Yi

We overcome these problems with a simple representation that aggregates point clouds at multiple scale levels with sparse voxel grids at different resolutions.

Neural Rendering valid

Instruction Distillation Makes Large Language Models Efficient Zero-shot Rankers

1 code implementation2 Nov 2023 Weiwei Sun, Zheng Chen, Xinyu Ma, Lingyong Yan, Shuaiqiang Wang, Pengjie Ren, Zhumin Chen, Dawei Yin, Zhaochun Ren

Furthermore, our approach surpasses the performance of existing supervised methods like monoT5 and is on par with the state-of-the-art zero-shot methods.

Prompt Engineering

Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method

no code implementations27 Oct 2023 Yukun Zhao, Lingyong Yan, Weiwei Sun, Guoliang Xing, Chong Meng, Shuaiqiang Wang, Zhicong Cheng, Zhaochun Ren, Dawei Yin

In this paper, we propose a novel self-detection method to detect which questions that a LLM does not know that are prone to generate nonfactual results.

Recoverable Privacy-Preserving Image Classification through Noise-like Adversarial Examples

1 code implementation19 Oct 2023 Jun Liu, Jiantao Zhou, Jinyu Tian, Weiwei Sun

Extensive experiments demonstrate that 1) the classification accuracy of the classifier trained in the plaintext domain remains the same in both the ciphertext and plaintext domains; 2) the encrypted images can be recovered into their original form with an average PSNR of up to 51+ dB for the SVHN dataset and 48+ dB for the VGGFace2 dataset; 3) our system exhibits satisfactory generalization capability on the encryption, decryption and classification tasks across datasets that are different from the training one; and 4) a high-level of security is achieved against three potential threat models.

Cloud Computing Image Classification +1

Generating Robust Adversarial Examples against Online Social Networks (OSNs)

1 code implementation19 Oct 2023 Jun Liu, Jiantao Zhou, Haiwei Wu, Weiwei Sun, Jinyu Tian

In this work, we aim to design a new framework for generating robust AEs that can survive the OSN transmission; namely, the AEs before and after the OSN transmission both possess strong attack capabilities.

SSIF: Learning Continuous Image Representation for Spatial-Spectral Super-Resolution

no code implementations30 Sep 2023 Gengchen Mai, Ni Lao, Weiwei Sun, Yuchi Ma, Jiaming Song, Chenlin Meng, Hongxu Ma, Jinmeng Rao, Ziyuan Li, Stefano Ermon

Existing digital sensors capture images at fixed spatial and spectral resolutions (e. g., RGB, multispectral, and hyperspectral images), and each combination requires bespoke machine learning models.

Spectral Super-Resolution Super-Resolution

RADE: Reference-Assisted Dialogue Evaluation for Open-Domain Dialogue

no code implementations15 Sep 2023 Zhengliang Shi, Weiwei Sun, Shuo Zhang, Zhen Zhang, Pengjie Ren, Zhaochun Ren

To this end, we propose the Reference-Assisted Dialogue Evaluation (RADE) approach under the multi-task learning framework, which leverages the pre-created utterance as reference other than the gold response to relief the one-to-many problem.

Dialogue Evaluation Multi-Task Learning +1

Is Argument Structure of Learner Chinese Understandable: A Corpus-Based Analysis

no code implementations17 Aug 2023 Yuguang Duan, Zi Lin, Weiwei Sun

The annotation procedure is guided by the Chinese PropBank specification, which is originally developed to cover first language phenomena.

Semantic Role Labeling

Answering Ambiguous Questions via Iterative Prompting

1 code implementation8 Jul 2023 Weiwei Sun, Hengyi Cai, Hongshen Chen, Pengjie Ren, Zhumin Chen, Maarten de Rijke, Zhaochun Ren

To provide feasible answers to an ambiguous question, one approach is to directly predict all valid answers, but this can struggle with balancing relevance and diversity.

Open-Domain Question Answering valid

Towards Explainable Conversational Recommender Systems

1 code implementation27 May 2023 Shuyu Guo, Shuo Zhang, Weiwei Sun, Pengjie Ren, Zhumin Chen, Zhaochun Ren

To achieve this, we conduct manual and automatic approaches to extend these dialogues and construct a new CRS dataset, namely Explainable Recommendation Dialogues (E-ReDial).

Explainable Recommendation Explanation Generation +2

Generative Knowledge Selection for Knowledge-Grounded Dialogues

1 code implementation10 Apr 2023 Weiwei Sun, Pengjie Ren, Zhaochun Ren

However, such approaches neglect the interactions between snippets, leading to difficulties in inferring the meaning of snippets.

Response Generation

Contrastive Learning Reduces Hallucination in Conversations

1 code implementation20 Dec 2022 Weiwei Sun, Zhengliang Shi, Shen Gao, Pengjie Ren, Maarten de Rijke, Zhaochun Ren

MixCL effectively reduces the hallucination of LMs in conversations and achieves the highest performance among LM-based dialogue agents in terms of relevancy and factuality.

Contrastive Learning Hallucination

CAT: Learning to Collaborate Channel and Spatial Attention from Multi-Information Fusion

no code implementations13 Dec 2022 Zizhang Wu, Man Wang, Weiwei Sun, Yuchen Li, Tianhao Xu, Fan Wang, Keke Huang

Channel and spatial attention mechanism has proven to provide an evident performance boost of deep convolution neural networks (CNNs).

Image Classification Instance Segmentation +3

RNTrajRec: Road Network Enhanced Trajectory Recovery with Spatial-Temporal Transformer

1 code implementation23 Nov 2022 Yuqi Chen, Hanyuan Zhang, Weiwei Sun, Baihua Zheng

However, many real-life trajectories are collected with low sample rate due to energy concern or other constraints. We study the task of trajectory recovery in this paper as a means for increasing the sample rate of low sample trajectories.

Decoder Graph Generation +2

Towards General-Purpose Representation Learning of Polygonal Geometries

1 code implementation29 Sep 2022 Gengchen Mai, Chiyu Jiang, Weiwei Sun, Rui Zhu, Yao Xuan, Ling Cai, Krzysztof Janowicz, Stefano Ermon, Ni Lao

For the spatial domain approach, we propose ResNet1D, a 1D CNN-based polygon encoder, which uses circular padding to achieve loop origin invariance on simple polygons.

Representation Learning

Adaptive Structural Similarity Preserving for Unsupervised Cross Modal Hashing

no code implementations9 Jul 2022 Liang Li, Baihua Zheng, Weiwei Sun

We introduce structural semantic metrics based on graph adjacency relations during the semantic reconstruction and correlation mining stage and meanwhile align the structure semantics in the hash space with an asymmetric binary optimization process.

Management Representation Learning

TUSK: Task-Agnostic Unsupervised Keypoints

no code implementations16 Jun 2022 Yuhe Jin, Weiwei Sun, Jan Hosang, Eduard Trulls, Kwang Moo Yi

Existing unsupervised methods for keypoint learning rely heavily on the assumption that a specific keypoint type (e. g. elbow, digit, abstract geometric shape) appears only once in an image.

Object Discovery Unsupervised Keypoints

Multi-Agent Reinforcement Learning for Traffic Signal Control through Universal Communication Method

1 code implementation26 Apr 2022 Qize Jiang, Minhao Qin, Shengmin Shi, Weiwei Sun, Baihua Zheng

How to coordinate the communication among intersections effectively in real complex traffic scenarios with multi-intersection is challenging.

Multi-agent Reinforcement Learning reinforcement-learning +1

Metaphorical User Simulators for Evaluating Task-oriented Dialogue Systems

2 code implementations2 Apr 2022 Weiwei Sun, Shuyu Guo, Shuo Zhang, Pengjie Ren, Zhumin Chen, Maarten de Rijke, Zhaochun Ren

Employing existing user simulators to evaluate TDSs is challenging as user simulators are primarily designed to optimize dialogue policies for TDSs and have limited evaluation capabilities.

Task-Oriented Dialogue Systems

Universal Semantic Tagging for English and Mandarin Chinese

1 code implementation NAACL 2021 Wenxi Li, Yiyang Hou, Yajie Ye, Li Liang, Weiwei Sun

By means of the new annotations, we also evaluate a series of neural tagging models to gauge how successful semantic tagging can be: accuracies of 92. 7{\%} and 94. 6{\%} are obtained for Chinese and English respectively.

LiteDepthwiseNet: An Extreme Lightweight Network for Hyperspectral Image Classification

no code implementations15 Oct 2020 Benlei Cui, XueMei Dong, Qiaoqiao Zhan, Jiangtao Peng, Weiwei Sun

Based on 3D depthwise convolution, LiteDepthwiseNet can decompose standard convolution into depthwise convolution and pointwise convolution, which can achieve high classification performance with minimal parameters.

Classification General Classification +1

Multiscale Context-Aware Ensemble Deep KELM for Efficient Hyperspectral Image Classification

1 code implementation22 Sep 2020 Bobo Xi, Jiaojiao Li, Yunsong Li, Rui Song, Weiwei Sun, Qian Du.

Recently, multiscale spatial features have been widely utilized to improve the hyperspectral image (HSI) classification performance.

Computational Efficiency General Classification +1

Constructing a Family Tree of Ten Indo-European Languages with Delexicalized Cross-linguistic Transfer Patterns

no code implementations17 Jul 2020 Yuanyuan Zhao, Weiwei Sun, Xiaojun Wan

It is reasonable to hypothesize that the divergence patterns formulated by historical linguists and typologists reflect constraints on human languages, and are thus consistent with Second Language Acquisition (SLA) in a certain way.

Language Acquisition

Parsing into Variable-in-situ Logico-Semantic Graphs

no code implementations ACL 2020 Yufei Chen, Weiwei Sun

We propose variable-in-situ logico-semantic graphs to bridge the gap between semantic graph and logical form parsing.

Negation valid

Exact yet Efficient Graph Parsing, Bi-directional Locality and the Constructivist Hypothesis

no code implementations ACL 2020 Yajie Ye, Weiwei Sun

A key problem in processing graph-based meaning representations is graph parsing, i. e. computing all possible derivations of a given graph according to a (competence) grammar.

Vehicle Re-ID for Surround-view Camera System

no code implementations30 Jun 2020 Zizhang Wu, Man Wang, Lingxiao Yin, Weiwei Sun, Jason Wang, Huangbin Wu

The vehicle re-identification (ReID) plays a critical role in the perception system of autonomous driving, which attracts more and more attention in recent years.

Autonomous Driving Vehicle Re-Identification

PSDet: Efficient and Universal Parking Slot Detection

no code implementations12 May 2020 Zizhang Wu, Weiwei Sun, Man Wang, Xiaoquan Wang, Lizhu Ding, Fan Wang

\romannumeral2, Expert knowledge for parking slot detection is under-estimated.

DeepDualMapper: A Gated Fusion Network for Automatic Map Extraction using Aerial Images and Trajectories

no code implementations17 Feb 2020 Hao Wu, Hanyuan Zhang, Xin-Yu Zhang, Weiwei Sun, Baihua Zheng, Yuning Jiang

We propose a deep convolutional neural network called DeepDualMapper which fuses the aerial image and trajectory data in a more seamless manner to extract the digital map.


Peking at MRP 2019: Factorization- and Composition-Based Parsing for Elementary Dependency Structures

no code implementations CONLL 2019 Yufei Chen, Yajie Ye, Weiwei Sun

We design, implement and evaluate two semantic parsers, which represent factorization- and composition-based approaches respectively, for Elementary Dependency Structures (EDS) at the CoNLL 2019 Shared Task on Cross-Framework Meaning Representation Parsing.

Optimizing Through Learned Errors for Accurate Sports Field Registration

1 code implementation17 Sep 2019 Wei Jiang, Juan Camilo Gamboa Higuera, Baptiste Angles, Weiwei Sun, Mehrsan Javan, Kwang Moo Yi

We propose an optimization-based framework to register sports field templates onto broadcast videos.

A Comparative Analysis of Knowledge-Intensive and Data-Intensive Semantic Parsers

no code implementations4 Jul 2019 Junjie Cao, Zi Lin, Weiwei Sun, Xiaojun Wan

We present a phenomenon-oriented comparative analysis of the two dominant approaches in task-independent semantic parsing: classic, knowledge-intensive and neural, data-intensive models.

Semantic Parsing

Graph-Based Meaning Representations: Design and Processing

1 code implementation ACL 2019 Alex Koller, er, Stephan Oepen, Weiwei Sun

This tutorial is on representing and processing sentence meaning in the form of labeled directed graphs.


Parsing Chinese Sentences with Grammatical Relations

no code implementations CL 2019 Weiwei Sun, Yufei Chen, Xiaojun Wan, Meichun Liu

In this work, we propose to represent grammatical information using general directed dependency graphs.

Ineffectiveness of Dictionary Coding to Infer Predictability Limits of Human Mobility

no code implementations8 Oct 2018 Yunheng Han, Weiwei Sun, Baihua Zheng

Consequently, it is ineffective to infer predictability through dictionary coding algorithms.

Semantic Role Labeling for Learner Chinese: the Importance of Syntactic Parsing and L2-L1 Parallel Data

1 code implementation EMNLP 2018 Zi Lin, Yuguang Duan, Yuan-Yuan Zhao, Weiwei Sun, Xiaojun Wan

This paper studies semantic parsing for interlanguage (L2), taking semantic role labeling (SRL) as a case task and learner Chinese as a case language.

Semantic Parsing Semantic Role Labeling +1

Accurate SHRG-Based Semantic Parsing

no code implementations ACL 2018 Yufei Chen, Weiwei Sun, Xiaojun Wan

We demonstrate that an SHRG-based parser can produce semantic graphs much more accurately than previously shown, by relating synchronous production rules to the syntacto-semantic composition process.

Semantic Composition Semantic Parsing

Pre- and In-Parsing Models for Neural Empty Category Detection

no code implementations ACL 2018 Yufei Chen, Yuan-Yuan Zhao, Weiwei Sun, Xiaojun Wan

Motivated by the positive impact of empty category on syntactic parsing, we study neural models for pre- and in-parsing detection of empty category, which has not previously been investigated.

Dependency Parsing Structured Prediction

Language Generation via DAG Transduction

no code implementations ACL 2018 Yajie Ye, Weiwei Sun, Xiaojun Wan

This remarkable result demonstrates the feasibility of applying a DAG transducer to resolve NLG, as well as the effectiveness of our design.

Semantic Parsing Text Generation

Quasi-Second-Order Parsing for 1-Endpoint-Crossing, Pagenumber-2 Graphs

no code implementations EMNLP 2017 Junjie Cao, Sheng Huang, Weiwei Sun, Xiaojun Wan

We propose a new Maximum Subgraph algorithm for first-order parsing to 1-endpoint-crossing, pagenumber-2 graphs.

Dependency Parsing

Parsing for Grammatical Relations via Graph Merging

no code implementations CONLL 2017 Weiwei Sun, Yantao Du, Xiaojun Wan

This paper is concerned with building deep grammatical relation (GR) analysis using data-driven approach.

The Covert Helps Parse the Overt

no code implementations CONLL 2017 Xun Zhang, Weiwei Sun, Xiaojun Wan

This paper is concerned with whether deep syntactic information can help surface parsing, with a particular focus on empty categories.

Dependency Parsing

Semantic Dependency Parsing via Book Embedding

no code implementations ACL 2017 Weiwei Sun, Junjie Cao, Xiaojun Wan

We model a dependency graph as a book, a particular kind of topological space, for semantic dependency parsing.

Combinatorial Optimization Dependency Parsing +2

Data-driven, PCFG-based and Pseudo-PCFG-based Models for Chinese Dependency Parsing

no code implementations TACL 2013 Weiwei Sun, Xiaojun Wan

We present a comparative study of transition-, graph- and PCFG-based models aimed at illuminating more precisely the likely contribution of CFGs in improving Chinese dependency parsing accuracy, especially by combining heterogeneous models.

Chinese Dependency Parsing Dependency Parsing +2

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