Search Results for author:
Found 68 papers, 28 papers with code
基于Graph Transformer的知识库问题生成(Question Generation from Knowledge Base with Graph Transformer)
知识库问答依靠知识库推断答案需大量带标注信息的问答对, 但构建大规模且精准的数据集不仅代价昂贵, 还受领域等因素限制。为缓解数据标注问题, 面向知识库的问题生成任务引起了研究者关注, 该任务是利用知识库三元组自动生成问题。现有方法仅由一个三元组生成的问题简短且缺乏多样性。为生成信息量丰富且多样化的问题, 本文采用Graph Transformer和BERT两个编码层来加强三元组多粒度语义表征以获取背景信息。在SimpleQuestions上的实验结果证明了该方法有效性。
IIE’s Neural Machine Translation Systems for WMT20
In this paper we introduce the systems IIE submitted for the WMT20 shared task on German-French news translation.
Comparison of the effects of attention mechanism on translation tasks of different lengths of ambiguous words
This paper focuses on the performance of encoder decoder attention mechanism in word sense disambiguation task with different text length, trying to find out the influence of context marker on attention mechanism in word sense disambiguation task.
Detecting Socially Abnormal Highway Driving Behaviors via Recurrent Graph Attention Networks
In this work, we consider the problem of detecting a variety of socially abnormal driving behaviors, i. e., behaviors that do not conform to the behavior of other nearby drivers.
Category Query Learning for Human-Object Interaction Classification
Unlike most previous HOI methods that focus on learning better human-object features, we propose a novel and complementary approach called category query learning.
Collaboration Helps Camera Overtake LiDAR in 3D Detection
Camera-only 3D detection provides an economical solution with a simple configuration for localizing objects in 3D space compared to LiDAR-based detection systems.
Subspace based Federated Unlearning
Federated learning (FL) enables multiple clients to train a machine learning model collaboratively without exchanging their local data.
ConsPrompt: Easily Exploiting Contrastive Samples for Few-shot Prompt Learning
The effectiveness of proposed ConsPrompt is demonstrated in five different few-shot learning tasks and shown the similarity-based sampling strategy is more effective than label-based in combining contrastive learning.
FADO: Feedback-Aware Double COntrolling Network for Emotional Support Conversation
The core module in FADO consists of a dual-level feedback strategy selector and a double control reader.
STPrompt: Semantic-guided and Task-driven prompts for Effective Few-shot Classification
The effectiveness of prompt learning has been demonstrated in different pre-trained language models.
Number-Adaptive Prototype Learning for 3D Point Cloud Semantic Segmentation
Instead of learning a single prototype for each class, in this paper, we propose to use an adaptive number of prototypes to dynamically describe the different point patterns within a semantic class.
Ranked #12 on
3D Semantic Segmentation
on SemanticKITTI
Psychology-guided Controllable Story Generation
Inspired by psychology theories, we introduce global psychological state chains, which include the needs and emotions of the protagonists, to help a story generation system create more controllable and well-planned stories.
Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps
Where2comm has two distinct advantages: i) it considers pragmatic compression and uses less communication to achieve higher perception performance by focusing on perceptually critical areas; and ii) it can handle varying communication bandwidth by dynamically adjusting spatial areas involved in communication.
Ranked #1 on
3D Object Detection
on DAIR-V2X
Learning Reconstructability for Drone Aerial Path Planning
To reconstruct a new urban scene, we first build the 3D scene proxy, then rely on the predicted reconstruction quality and uncertainty measures by our network, based off of the proxy geometry, to guide the drone path planning.
COMMA: Modeling Relationship among Motivations, Emotions and Actions in Language-based Human Activities
Motivations, emotions, and actions are inter-related essential factors in human activities.
T$^2$LR-Net: An Unrolling Reconstruction Network Learning Transformed Tensor Low-Rank prior for Dynamic MR Imaging
By generalizing the FFT into an arbitrary unitary transformation of the transformed t-SVD and proposing the transformed tensor nuclear norm (TTNN), we introduce a flexible model based on TTNN with the ability to exploit the tensor low-rank prior of a transformed domain in a larger transformation space and elaborately design an iterative optimization algorithm based on the alternating direction method of multipliers (ADMM), which is further unrolled into a model-based deep unrolling reconstruction network to learn the transformed tensor low-rank prior (T$^2$LR-Net).
Multi-level Contrastive Learning Framework for Sequential Recommendation
Different from the previous contrastive learning-based methods for SR, MCLSR learns the representations of users and items through a cross-view contrastive learning paradigm from four specific views at two different levels (i. e., interest- and feature-level).
Aerial Monocular 3D Object Detection
To fill the gap, this work proposes a dual-view detection system named DVDET to achieve aerial monocular object detection in both the 2D image space and the 3D physical space.
Neural Message Passing for Visual Relationship Detection
Visual relationship detection aims to detect the interactions between objects in an image; however, this task suffers from combinatorial explosion due to the variety of objects and interactions.
Latency-Aware Collaborative Perception
Collaborative perception has recently shown great potential to improve perception capabilities over single-agent perception.
Do You Know My Emotion? Emotion-Aware Strategy Recognition towards a Persuasive Dialogue System
Specifically, CFO-Net designs a feedback memory module, including strategy pool and feedback pool, to obtain emotion-aware strategy representation.
FedHiSyn: A Hierarchical Synchronous Federated Learning Framework for Resource and Data Heterogeneity
As the efficiency of training in the ring topology prefers devices with homogeneous resources, the classification based on the computing capacity mitigates the impact of straggler effects.
Dynamic Cardiac MRI Reconstruction Using Combined Tensor Nuclear Norm and Casorati Matrix Nuclear Norm Regularizations
Recently, a new tensor nuclear norm based on t-SVD has been proposed and applied to tensor completion.
Dynamic MRI using Learned Transform-based Tensor Low-Rank Network (LT$^2$LR-Net)
While low-rank matrix prior has been exploited in dynamic MR image reconstruction and has obtained satisfying performance, tensor low-rank models have recently emerged as powerful alternative representations for three-dimensional dynamic MR datasets.
CogIntAc: Modeling the Relationships between Intention, Emotion and Action in Interactive Process from Cognitive Perspective
In this paper, we propose a novel cognitive framework of individual interaction.
Control Globally, Understand Locally: A Global-to-Local Hierarchical Graph Network for Emotional Support Conversation
Emotional support conversation aims at reducing the emotional distress of the help-seeker, which is a new and challenging task.
Dir-MUSIC Algorithm for DOA Estimation of Partial Discharge Based on Signal Strength represented by Antenna Gain Array Manifold
The experimental results show that the PD direction-finding error is 3. 39{\deg}, which can meet the need for Partial discharge DOA estimation using inspection robots in substations.
Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translation
Although data augmentation is widely used to enrich the training data, conventional methods with discrete manipulations fail to generate diverse and faithful training samples.
MuKEA: Multimodal Knowledge Extraction and Accumulation for Knowledge-based Visual Question Answering
Knowledge-based visual question answering requires the ability of associating external knowledge for open-ended cross-modal scene understanding.
CLSEG: Contrastive Learning of Story Ending Generation
To address these two issues, we propose a novel Contrastive Learning framework for Story Ending Generation (CLSEG), which has two steps: multi-aspect sampling and story-specific contrastive learning.
Modeling Intention, Emotion and External World in Dialogue Systems
Intention, emotion and action are important elements in human activities.
Streaming data preprocessing via online tensor recovery for large environmental sensor networks
Measuring the built and natural environment at a fine-grained scale is now possible with low-cost urban environmental sensor networks.
Know Deeper: Knowledge-Conversation Cyclic Utilization Mechanism for Open-domain Dialogue Generation
End-to-End intelligent neural dialogue systems suffer from the problems of generating inconsistent and repetitive responses.
Capturing, Reconstructing, and Simulating: the UrbanScene3D Dataset
We present UrbanScene3D, a large-scale data platform for research of urban scene perception and reconstruction.
Coarse-to-Careful: Seeking Semantic-related Knowledge for Open-domain Commonsense Question Answering
It is prevalent to utilize external knowledge to help machine answer questions that need background commonsense, which faces a problem that unlimited knowledge will transmit noisy and misleading information.
MCR-Net: A Multi-Step Co-Interactive Relation Network for Unanswerable Questions on Machine Reading Comprehension
Most of the existing systems design a simple classifier to determine answerability implicitly without explicitly modeling mutual interaction and relation between the question and passage, leading to the poor performance for determining the unanswerable questions.
End-to-End Human Object Interaction Detection with HOI Transformer
We propose HOI Transformer to tackle human object interaction (HOI) detection in an end-to-end manner.
Ranked #22 on
Human-Object Interaction Detection
on HICO-DET
(using extra training data)
IIE-NLP-Eyas at SemEval-2021 Task 4: Enhancing PLM for ReCAM with Special Tokens, Re-Ranking, Siamese Encoders and Back Translation
This paper introduces our systems for all three subtasks of SemEval-2021 Task 4: Reading Comprehension of Abstract Meaning.
Revealing Gravitational Collapse in Serpens G3-G6 Molecular Cloud using Velocity Gradients
We suggest that the Serpens G3-G6 south clump is undergoing a gravitational collapse.
Astrophysics of Galaxies
Measuring magnetization with rotation measures and velocity centroids in supersonic MHD turbulence
The interstellar turbulence is magnetized and thus anisotropic.
Astrophysics of Galaxies
Graph Convolutional Networks for traffic anomaly
Event detection has been an important task in transportation, whose task is to detect points in time when large events disrupts a large portion of the urban traffic network.
Anisotropies in Compressible MHD Turbulence: Probing Magnetic Fields and Measuring Magnetization
We demonstrate that the anisotropic structure functions of turbulent velocities can be used to estimate both the orientation and strength of magnetic fields.
Astrophysics of Galaxies
Bi-directional CognitiveThinking Network for Machine Reading Comprehension
We propose a novel Bi-directional Cognitive Knowledge Framework (BCKF) for reading comprehension from the perspective of complementary learning systems theory.
Learning User Representations with Hypercuboids for Recommender Systems
Furthermore, we present two variants of hypercuboids to enhance the capability in capturing the diversities of user interests.
Bi-directional Cognitive Thinking Network for Machine Reading Comprehension
We propose a novel Bi-directional Cognitive Knowledge Framework (BCKF) for reading comprehension from the perspective of complementary learning systems theory.
Uncertainty-Aware Semantic Augmentation for Neural Machine Translation
As a sequence-to-sequence generation task, neural machine translation (NMT) naturally contains intrinsic uncertainty, where a single sentence in one language has multiple valid counterparts in the other.
CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation
We first build a cognitive structure CogTree to organize the relationships based on the prediction of a biased SGG model.
Ranked #2 on
Scene Graph Generation
on Visual Genome
(mean Recall @20 metric)
Cross-modal Knowledge Reasoning for Knowledge-based Visual Question Answering
Finally, we perform graph neural networks to infer the global-optimal answer by jointly considering all the concepts.
Study Turbulence and Probe Magnetic Field Using Gradient Technique: Application to HI-to-H2 Transition Regions
In this work, we consider the effect of turbulence on the HI and H2 transition and explore the possibility of tracing the magnetic field direction in photodissociation regions using the Gradient Technique.
Astrophysics of Galaxies
On Learning Universal Representations Across Languages
Recent studies have demonstrated the overwhelming advantage of cross-lingual pre-trained models (PTMs), such as multilingual BERT and XLM, on cross-lingual NLP tasks.
Contrastive Learning
Cross-Lingual Natural Language Inference
+3
DAM: Deliberation, Abandon and Memory Networks for Generating Detailed and Non-repetitive Responses in Visual Dialogue
The ability of generating detailed and non-repetitive responses is crucial for the agent to achieve human-like conversation.
IIE-NLP-NUT at SemEval-2020 Task 4: Guiding PLM with Prompt Template Reconstruction Strategy for ComVE
This paper introduces our systems for the first two subtasks of SemEval Task4: Commonsense Validation and Explanation.
Mucko: Multi-Layer Cross-Modal Knowledge Reasoning for Fact-based Visual Question Answering
In this paper, we depict an image by a multi-modal heterogeneous graph, which contains multiple layers of information corresponding to the visual, semantic and factual features.
Multiscale Collaborative Deep Models for Neural Machine Translation
Recent evidence reveals that Neural Machine Translation (NMT) models with deeper neural networks can be more effective but are difficult to train.
Collaborative Motion Prediction via Neural Motion Message Passing
Motion prediction is essential and challenging for autonomous vehicles and social robots.
DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue
More importantly, we can tell which modality (visual or semantic) has more contribution in answering the current question by visualizing the gate values.
Ranked #6 on
Visual Dialog
on VisDial v0.9 val
Unsupervised Neural Machine Translation with Future Rewarding
In this paper, we alleviate the local optimality of back-translation by learning a policy (takes the form of an encoder-decoder and is defined by its parameters) with future rewarding under the reinforcement learning framework, which aims to optimize the global word predictions for unsupervised neural machine translation.
Robust Tensor Recovery with Fiber Outliers for Traffic Events
In this article, we develop a method to detect extreme events in large traffic datasets, and to impute missing data during regular conditions.
Influence of Boundaries and Thermostatting on Nonequilibrium Molecular Dynamics Simulations of Heat Conduction in Solids
Conventionally, the thermal conductivity of a finite system is calculated as the ratio between the heat flux and the temperature gradient extracted from the linear part of the temperature profile away from the local thermostats.
Mesoscale and Nanoscale Physics Statistical Mechanics Computational Physics
GraphNAS: Graph Neural Architecture Search with Reinforcement Learning
On node classification tasks, GraphNAS can design a novel network architecture that rivals the best human-invented architecture in terms of test set accuracy.
Ranked #11 on
Node Classification
on PPI
Scene Graph Reasoning with Prior Visual Relationship for Visual Question Answering
Upon the constructed graph, we propose a Scene Graph Convolutional Network (SceneGCN) to jointly reason the object properties and relational semantics for the correct answer.
Combining Subgoal Graphs with Reinforcement Learning to Build a Rational Pathfinder
The first advantage of the proposed method is that SSG can solve the limitations of sparse reward and local minima trap for RL agents; thus, LSPI can be used to generate paths in complex environments.
Textual Relationship Modeling for Cross-Modal Information Retrieval
A joint neural model is proposed to learn feature representation individually in each modality.
Multimedia
A Benchmarking of DCM Based Architectures for Position and Velocity Controlled Walking of Humanoid Robots
More precisely, we present and compare several DCM based implementations of a three layer control architecture.
Robotics
Mining and Analyzing the Future Works in Scientific Articles
Third, we apply the extraction method and the classification model to a paper dataset in the computer science field and conduct a further analysis of the future works.
