Search Results for author:
Found 288 papers, 112 papers with code
A Progressive Framework for Role-Aware Rumor Resolution
Existing works on rumor resolution have shown great potential in recognizing word appearance and user participation.
PlugAT: A Plug and Play Module to Defend against Textual Adversarial Attack
To reduce the potential side effects of using defense modules, we further propose a novel forgetting restricted adversarial training, which filters out bad adversarial examples that impair the performance of original ones.
LFKQG: A Controlled Generation Framework with Local Fine-tuning for Question Generation over Knowledge Bases
Existing KBQG models still face two main challenges: (1) Most models often focus on the most relevant part of the answer entity, while neglecting the rest of the subgraph.
ECNU_ICA at SemEval-2022 Task 10: A Simple and Unified Model for Monolingual and Crosslingual Structured Sentiment Analysis
The task aims to extract the structured sentiment information (e. g., holder, target, expression and sentiment polarity) in a text.
Read Extensively, Focus Smartly: A Cross-document Semantic Enhancement Method for Visual Documents NER
To deal with this problem, this work proposes a cross-document semantic enhancement method, which consists of two modules: 1) To prevent distractions from irrelevant regions in the current document, we design a learnable attention mask mechanism, which is used to adaptively filter redundant information in the current document.
Flooding-X: Improving BERT’s Resistance to Adversarial Attacks via Loss-Restricted Fine-Tuning
Adversarial robustness has attracted much attention recently, and the mainstream solution is adversarial training.
An Empirical Assessment of the Qualitative Aspects of Misinformation in Health News
We present a health news classification task to determine whether medical news articles satisfy a set of review criteria deemed important by medical experts and health care journalists.
CQG: A Simple and Effective Controlled Generation Framework for Multi-hop Question Generation
CQG employs a simple method to generate the multi-hop questions that contain key entities in multi-hop reasoning chains, which ensure the complexity and quality of the questions.
A Knowledge-Aware Sequence-to-Tree Network for Math Word Problem Solving
With the advancements in natural language processing tasks, math word problem solving has received increasing attention.
An Edge-Enhanced Hierarchical Graph-to-Tree Network for Math Word Problem Solving
Specifically, an edge-enhanced hierarchical graph encoder is used to incorporate edge label information.
Iterative GNN-based Decoder for Question Generation
However, (1) they ignore the rich structure information that is hidden in the previously generated text.
Making Parameter-efficient Tuning More Efficient: A Unified Framework for Classification Tasks
Specifically, we re-formulate both token and sentence classification tasks into a unified language modeling task, and map label spaces of different tasks into the same vocabulary space.
A Structure-Aware Argument Encoder for Literature Discourse Analysis
Existing research for argument representation learning mainly treats tokens in the sentence equally and ignores the implied structure information of argumentative context.
PathQG: Neural Question Generation from Facts
Human evaluation also proves that our model is able to generate relevant and informative questions.
Anti-Aliased Neural Implicit Surfaces with Encoding Level of Detail
Drawing inspiration from voxel-based representations with the level of detail (LoD), we introduce a multi-scale tri-plane-based scene representation that is capable of capturing the LoD of the signed distance function (SDF) and the space radiance.
Syntax Tree Constrained Graph Network for Visual Question Answering
Existing VQA methods integrate vision modeling and language understanding to explore the deep semantics of the question.
Cure the headache of Transformers via Collinear Constrained Attention
As the rapid progression of practical applications based on Large Language Models continues, the importance of extrapolating performance has grown exponentially in the research domain.
The Rise and Potential of Large Language Model Based Agents: A Survey
Many efforts have been made to develop intelligent agents, but they mainly focus on advancement in algorithms or training strategies to enhance specific capabilities or performance on particular tasks.
An Empirical Study of NetOps Capability of Pre-Trained Large Language Models
Nowadays, the versatile capabilities of Pre-trained Large Language Models (LLMs) have attracted much attention from the industry.
One-Bit-Aided Modulo Sampling for DOA Estimation
To overcome this fundamental bottleneck, we propose a one-bit-aided (1bit-aided) modulo sampling scheme for direction-of-arrival (DOA) estimation.
VideoGen: A Reference-Guided Latent Diffusion Approach for High Definition Text-to-Video Generation
In this paper, we present VideoGen, a text-to-video generation approach, which can generate a high-definition video with high frame fidelity and strong temporal consistency using reference-guided latent diffusion.
${\rm E}(3)$-Equivariant Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning
Identification and analysis of symmetrical patterns in the natural world have led to significant discoveries across various scientific fields, such as the formulation of gravitational laws in physics and advancements in the study of chemical structures.
Data-driven decision-focused surrogate modeling
We introduce the concept of decision-focused surrogate modeling for solving computationally challenging nonlinear optimization problems in real-time settings.
No-frills Temporal Video Grounding: Multi-Scale Neighboring Attention and Zoom-in Boundary Detection
Temporal video grounding (TVG) aims to retrieve the time interval of a language query from an untrimmed video.
Secrets of RLHF in Large Language Models Part I: PPO
Therefore, we explore the PPO-max, an advanced version of PPO algorithm, to efficiently improve the training stability of the policy model.
A Comprehensive Survey of Artificial Intelligence Techniques for Talent Analytics
To this end, we present an up-to-date and comprehensive survey on AI technologies used for talent analytics in the field of human resource management.
On the Universal Adversarial Perturbations for Efficient Data-free Adversarial Detection
Detecting adversarial samples that are carefully crafted to fool the model is a critical step to socially-secure applications.
DSRM: Boost Textual Adversarial Training with Distribution Shift Risk Minimization
Adversarial training is one of the best-performing methods in improving the robustness of deep language models.
Constraint-aware and Ranking-distilled Token Pruning for Efficient Transformer Inference
Deploying pre-trained transformer models like BERT on downstream tasks in resource-constrained scenarios is challenging due to their high inference cost, which grows rapidly with input sequence length.
Learning Profitable NFT Image Diffusions via Multiple Visual-Policy Guided Reinforcement Learning
The proposed framework consists of a large language model (LLM), a diffusion-based image generator, and a series of visual rewards by design.
Successive one-sided Hodrick-Prescott filter with incremental filtering algorithm for nonlinear economic time series
We propose a successive one-sided Hodrick-Prescott (SOHP) filter from multiple time scale decomposition perspective to derive trend estimate for a time series.
Process Knowledge-infused Learning for Clinician-friendly Explanations
In this study, we introduce Process Knowledge-infused Learning (PK-iL), a new learning paradigm that layers clinical process knowledge structures on language model outputs, enabling clinician-friendly explanations of the underlying language model predictions.
Explainable Artificial Intelligence (XAI)
Language Modelling
Actively Supervised Clustering for Open Relation Extraction
The key to the setting is selecting which instances to label.
Open Set Relation Extraction via Unknown-Aware Training
Inspired by text adversarial attacks, we adaptively apply small but critical perturbations to original training instances and thus synthesizing negative instances that are more likely to be mistaken by the model as known relations.
RE-Matching: A Fine-Grained Semantic Matching Method for Zero-Shot Relation Extraction
However, general matching methods lack explicit modeling of the above matching pattern.
On the Generalization of Multi-modal Contrastive Learning
Multi-modal contrastive learning (MMCL) has recently garnered considerable interest due to its superior performance in visual tasks, achieved by embedding multi-modal data, such as visual-language pairs.
Context-Aware Bayesian Network Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning
Executing actions in a correlated manner is a common strategy for human coordination that often leads to better cooperation, which is also potentially beneficial for cooperative multi-agent reinforcement learning (MARL).
Asymptotic Performance Analysis of Large-Scale Active IRS-Aided Wireless Network
Numerical simulation results show that a 3-bit discrete phase shifter is required to achieve a trivial performance loss for a large-scale active IRS.
Towards Better Entity Linking with Multi-View Enhanced Distillation
Aiming at learning entity representations that can match divergent mentions, this paper proposes a Multi-View Enhanced Distillation (MVD) framework, which can effectively transfer knowledge of multiple fine-grained and mention-relevant parts within entities from cross-encoders to dual-encoders.
Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement
For example, with Text-davinci-003, our method boosts the performance of standard few-shot prompting by $8. 0\%$ on GSM8K and $17. 8\%$ on MultiArith; it also improves the performance of CoT by $6. 0\%$ on GSM8K and $6. 0\%$ on MathQA, respectively.
Causal Intervention for Abstractive Related Work Generation
Abstractive related work generation has attracted increasing attention in generating coherent related work that better helps readers grasp the background in the current research.
Query Structure Modeling for Inductive Logical Reasoning Over Knowledge Graphs
The results demonstrate the effectiveness of our method on logical reasoning over KGs in both inductive and transductive settings.
To Copy Rather Than Memorize: A Vertical Learning Paradigm for Knowledge Graph Completion
Embedding models have shown great power in knowledge graph completion (KGC) task.
Farewell to Aimless Large-scale Pretraining: Influential Subset Selection for Language Model
Pretrained language models have achieved remarkable success in various natural language processing tasks.
Spatiotemporal Attention-based Semantic Compression for Real-time Video Recognition
This paper studies the computational offloading of video action recognition in edge computing.
A Confidence-based Partial Label Learning Model for Crowd-Annotated Named Entity Recognition
Particularly, we propose a Confidence-based Partial Label Learning (CPLL) method to integrate the prior confidence (given by annotators) and posterior confidences (learned by models) for crowd-annotated NER.
Movie101: A New Movie Understanding Benchmark
Closer to real scenarios, the Movie Clip Narrating (MCN) task in our benchmark asks models to generate role-aware narration paragraphs for complete movie clips where no actors are speaking.
Modeling the Q-Diversity in a Min-max Play Game for Robust Optimization
Models trained with empirical risk minimization (ERM) are revealed to easily rely on spurious correlations, resulting in poor generalization.
DMDD: A Large-Scale Dataset for Dataset Mentions Detection
We use DMDD to establish baseline performance for dataset mention detection and linking.
Accurate Gigapixel Crowd Counting by Iterative Zooming and Refinement
The increasing prevalence of gigapixel resolutions has presented new challenges for crowd counting.
Dual-Alignment Pre-training for Cross-lingual Sentence Embedding
Recent studies have shown that dual encoder models trained with the sentence-level translation ranking task are effective methods for cross-lingual sentence embedding.
Maybe Only 0.5% Data is Needed: A Preliminary Exploration of Low Training Data Instruction Tuning
Instruction tuning for large language models (LLMs) has gained attention from researchers due to its ability to unlock the potential of LLMs in following instructions.
Enhancing Contrastive Learning with Noise-Guided Attack: Towards Continual Relation Extraction in the Wild
The principle of continual relation extraction~(CRE) involves adapting to emerging novel relations while preserving od knowledge.
Pre-training Language Model as a Multi-perspective Course Learner
Besides, two self-correction courses are proposed to bridge the chasm between the two encoders by creating a "correction notebook" for secondary-supervision.
CausalAPM: Generalizable Literal Disentanglement for NLU Debiasing
Dataset bias, i. e., the over-reliance on dataset-specific literal heuristics, is getting increasing attention for its detrimental effect on the generalization ability of NLU models.
UrbanBIS: a Large-scale Benchmark for Fine-grained Urban Building Instance Segmentation
Besides, we propose B-Seg, a building instance segmentation method to establish UrbanBIS.
Rumor Detection with Hierarchical Representation on Bipartite Adhoc Event Trees
Accordingly, we propose a novel rumor detection model with hierarchical representation on the bipartite adhoc event trees called BAET.
Local Implicit Ray Function for Generalizable Radiance Field Representation
To solve this problem, we propose LIRF to aggregate the information from conical frustums to construct a ray.
Inverting the Imaging Process by Learning an Implicit Camera Model
In principle, our new implicit neural camera model has the potential to benefit a wide array of other inverse imaging tasks.
NeAI: A Pre-convoluted Representation for Plug-and-Play Neural Ambient Illumination
Recent advances in implicit neural representation have demonstrated the ability to recover detailed geometry and material from multi-view images.
InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction
Large language models have unlocked strong multi-task capabilities from reading instructive prompts.
The Second Monocular Depth Estimation Challenge
This paper discusses the results for the second edition of the Monocular Depth Estimation Challenge (MDEC).
Disorder-invariant Implicit Neural Representation
However, the expressive power of INR is limited by the spectral bias in the network training.
A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models
GPT series models, such as GPT-3, CodeX, InstructGPT, ChatGPT, and so on, have gained considerable attention due to their exceptional natural language processing capabilities.
IRGen: Generative Modeling for Image Retrieval
While generative modeling has been ubiquitous in natural language processing and computer vision, its application to image retrieval remains unexplored.
UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation
Large Language Models (LLMs) are popular for their impressive abilities, but the need for model-specific fine-tuning or task-specific prompt engineering can hinder their generalization.
A Message Passing Perspective on Learning Dynamics of Contrastive Learning
In recent years, contrastive learning achieves impressive results on self-supervised visual representation learning, but there still lacks a rigorous understanding of its learning dynamics.
A Visual SLAM with Moving Object Trajectory Prediction
Visual Simultaneous Localization and Mapping (SLAM) has received significant attention in recent years due to its ability to estimate camera trajectory and create an environment map using visual data alone, making a substantial contribution to autonomous driving applications, in particular, a real-world scenario with moving crowds and vehicles.
How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks
The GPT-3. 5 models have demonstrated impressive performance in various Natural Language Processing (NLP) tasks, showcasing their strong understanding and reasoning capabilities.
Natural Language Inference
Natural Language Understanding
+1
Uncertainty-Aware Reward-based Deep Reinforcement Learning for Intent Analysis of Social Media Information
Distinguishing the types of fake news spreaders based on their intent is critical because it will effectively guide how to intervene to mitigate the spread of fake news with different approaches.
Enhancing Model Performance in Multilingual Information Retrieval with Comprehensive Data Engineering Techniques
In this paper, we present our solution to the Multilingual Information Retrieval Across a Continuum of Languages (MIRACL) challenge of WSDM CUP 2023\footnote{https://project-miracl. github. io/}.
CCDN: Checkerboard Corner Detection Network for Robust Camera Calibration
Aiming to improve the checkerboard corner detection robustness against the images with poor quality, such as lens distortion, extreme poses, and noise, we propose a novel detection algorithm which can maintain high accuracy on inputs under multiply scenarios without any prior knowledge of the checkerboard pattern.
A Survey on Deep Learning based Time Series Analysis with Frequency Transformation
Despite the growing attention and the proliferation of research in this emerging field, there is currently a lack of a systematic review and in-depth analysis of deep learning-based time series models with FT.
Study of Optical Networks, 5G, Artificial Intelligence and Their Applications
This paper discusses the application of artificial intelligence (AI) technology in optical communication networks and 5G.
PromptMix: Text-to-image diffusion models enhance the performance of lightweight networks
In this paper, we introduce PromptMix, a method for artificially boosting the size of existing datasets, that can be used to improve the performance of lightweight networks.
DeciLS-PBO: an Effective Local Search Method for Pseudo-Boolean Optimization
Local search is an effective method for solving large-scale combinatorial optimization problems, and it has made remarkable progress in recent years through several subtle mechanisms.
Learning Informative Representation for Fairness-aware Multivariate Time-series Forecasting: A Group-based Perspective
To address this significant gap, we formulate the MTS fairness modeling problem as learning informative representations attending to both advantaged and disadvantaged variables.
Wide-Angle Rectification via Content-Aware Conformal Mapping
Despite the proliferation of ultra wide-angle lenses on smartphone cameras, such lenses often come with severe image distortion (e. g. curved linear structure, unnaturally skewed faces).
Cross-Linguistic Syntactic Difference in Multilingual BERT: How Good is It and How Does It Affect Transfer?
We demonstrate that the distance between the distributions of different languages is highly consistent with the syntactic difference in terms of linguistic formalisms.
SLAN: Self-Locator Aided Network for Cross-Modal Understanding
By aggregating cross-modal information, the region filter selects key regions and the region adaptor updates their coordinates with text guidance.
Fine-Grained Face Swapping via Regional GAN Inversion
We rethink face swapping from the perspective of fine-grained face editing, \textit{i. e., ``editing for swapping'' (E4S)}, and propose a framework that is based on the explicit disentanglement of the shape and texture of facial components.
Attention-based Feature Compression for CNN Inference Offloading in Edge Computing
We design a feature compression module based on the channel attention method in CNN, to compress the intermediate data by selecting the most important features.
Semantic Communication Enabling Robust Edge Intelligence for Time-Critical IoT Applications
The proposed Edge Intelligence framework consists of the proposed effectiveness encoding and effectiveness decoding.
Design and Prototyping Distributed CNN Inference Acceleration in Edge Computing
It is shown that the model selection with distributed inference HALP can significantly improve service reliability compared to the conventional stand-alone computation.
Local-to-Global Registration for Bundle-Adjusting Neural Radiance Fields
Neural Radiance Fields (NeRF) have achieved photorealistic novel views synthesis; however, the requirement of accurate camera poses limits its application.
DINER: Disorder-Invariant Implicit Neural Representation
Implicit neural representation (INR) characterizes the attributes of a signal as a function of corresponding coordinates which emerges as a sharp weapon for solving inverse problems.
Efficient Adversarial Training with Robust Early-Bird Tickets
Adversarial training is one of the most powerful methods to improve the robustness of pre-trained language models (PLMs).
Towards Understanding Omission in Dialogue Summarization
By analyzing this dataset, we find that a large improvement in summarization quality can be achieved by providing ground-truth omission labels for the summarization model to recover omission information, which demonstrates the importance of omission detection for omission mitigation in dialogue summarization.
Perceptual Video Coding for Machines via Satisfied Machine Ratio Modeling
Furthermore, we introduce an auxiliary task to increase the prediction accuracy by predicting the SMR difference between two images in different quality levels.
Robust Lottery Tickets for Pre-trained Language Models
Recent works on Lottery Ticket Hypothesis have shown that pre-trained language models (PLMs) contain smaller matching subnetworks(winning tickets) which are capable of reaching accuracy comparable to the original models.
Line Spectral Estimation via Unlimited Sampling
In addition, a two-stage US LSE (USLSE) is proposed where the line spectral signal is first recovered by iteratively executing DP and OMP, and then the parameters are estimated by applying a state-of-art LSE algorithm.
Efficient Learning of Decision-Making Models: A Penalty Block Coordinate Descent Algorithm for Data-Driven Inverse Optimization
In this work, we consider the inverse problem where we use prior decision data to uncover the underlying decision-making process in the form of a mathematical optimization model.
Graph Reinforcement Learning-based CNN Inference Offloading in Dynamic Edge Computing
To solve the maximization problem, we propose a graph reinforcement learning-based early-exit mechanism (GRLE), which outperforms the state-of-the-art work, deep reinforcement learning-based online offloading (DROO) and its enhanced method, DROO with early-exit mechanism (DROOE), under different dynamic scenarios.
Data-Driven Quickest Change Detection in Markov Models
The problem of quickest change detection in Markov models is studied.
RAPO: An Adaptive Ranking Paradigm for Bilingual Lexicon Induction
Bilingual lexicon induction induces the word translations by aligning independently trained word embeddings in two languages.
How Mask Matters: Towards Theoretical Understandings of Masked Autoencoders
Masked Autoencoders (MAE) based on a reconstruction task have risen to be a promising paradigm for self-supervised learning (SSL) and achieve state-of-the-art performance across different benchmark datasets.
Kernel-Whitening: Overcome Dataset Bias with Isotropic Sentence Embedding
Dataset bias has attracted increasing attention recently for its detrimental effect on the generalization ability of fine-tuned models.
Learning "O" Helps for Learning More: Handling the Concealed Entity Problem for Class-incremental NER
In this work, we conduct an empirical study on the "Unlabeled Entity Problem" and find that it leads to severe confusion between "O" and entities, decreasing class discrimination of old classes and declining the model's ability to learn new classes.
Edge-Varying Fourier Graph Networks for Multivariate Time Series Forecasting
The key problem in multivariate time series (MTS) analysis and forecasting aims to disclose the underlying couplings between variables that drive the co-movements.
Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models
With the trends of large NLP models, the increasing memory and computation costs hinder their efficient deployment on resource-limited devices.
An Ion Exchange Mechanism Inspired Story Ending Generator for Different Characters
Story ending generation aims at generating reasonable endings for a given story context.
Distributional Drift Adaptation with Temporal Conditional Variational Autoencoder for Multivariate Time Series Forecasting
Most existing MTS forecasting models greatly suffer from distribution drift and degrade the forecasting performance over time.
A Multi-Format Transfer Learning Model for Event Argument Extraction via Variational Information Bottleneck
Event argument extraction (EAE) aims to extract arguments with given roles from texts, which have been widely studied in natural language processing.
AIM 2022 Challenge on Super-Resolution of Compressed Image and Video: Dataset, Methods and Results
The homepage of this challenge is at https://github. com/RenYang-home/AIM22_CompressSR.
Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering
In this paper, we propose an interpretable stepwise reasoning framework to incorporate both single-hop supporting sentence identification and single-hop question generation at each intermediate step, and utilize the inference of the current hop for the next until reasoning out the final result.
Causal Intervention Improves Implicit Sentiment Analysis
In this work, we propose a causal intervention model for Implicit Sentiment Analysis using Instrumental Variable (ISAIV).
Crowd Counting on Heavily Compressed Images with Curriculum Pre-Training
JPEG image compression algorithm is a widely used technique for image size reduction in edge and cloud computing settings.
Exploring Anchor-based Detection for Ego4D Natural Language Query
In this paper we provide the technique report of Ego4D natural language query challenge in CVPR 2022.
A Semantic Alignment System for Multilingual Query-Product Retrieval
Our models are all trained with cross-entropy loss to classify the query-product pairs into ESCI 4 categories at first, and then we use weighted sum with the 4-class probabilities to get the score for ranking.
Efficient High-Resolution Deep Learning: A Survey
Cameras in modern devices such as smartphones, satellites and medical equipment are capable of capturing very high resolution images and videos.
PanGu-Coder: Program Synthesis with Function-Level Language Modeling
We present PanGu-Coder, a pretrained decoder-only language model adopting the PanGu-Alpha architecture for text-to-code generation, i. e. the synthesis of programming language solutions given a natural language problem description.
Receptive Field-based Segmentation for Distributed CNN Inference Acceleration in Collaborative Edge Computing
To reduce the computation time and communication overhead, we propose a novel collaborative edge computing using fused-layer parallelization to partition a CNN model into multiple blocks of convolutional layers.
Distributed Deep Learning Inference Acceleration using Seamless Collaboration in Edge Computing
This paper studies inference acceleration using distributed convolutional neural networks (CNNs) in collaborative edge computing.
Unifying Event Detection and Captioning as Sequence Generation via Pre-Training
Dense video captioning aims to generate corresponding text descriptions for a series of events in the untrimmed video, which can be divided into two sub-tasks, event detection and event captioning.
Neural Color Operators for Sequential Image Retouching
The neural color operator mimics the behavior of traditional color operators and learns pixelwise color transformation while its strength is controlled by a scalar.
Nonlinear Sufficient Dimension Reduction for Distribution-on-Distribution Regression
We introduce a new approach to nonlinear sufficient dimension reduction in cases where both the predictor and the response are distributional data, modeled as members of a metric space.
Neural Parameterization for Dynamic Human Head Editing
Implicit radiance functions emerged as a powerful scene representation for reconstructing and rendering photo-realistic views of a 3D scene.
Supervised Deep Hashing for High-dimensional and Heterogeneous Case-based Reasoning
Case-based Reasoning (CBR) on high-dimensional and heterogeneous data is a trending yet challenging and computationally expensive task in the real world.
Convergence and Price of Anarchy Guarantees of the Softmax Policy Gradient in Markov Potential Games
Our focus in this paper is to study the convergence of the policy gradient method for solving MPGs under softmax policy parameterization, both tabular and parameterized with general function approximators such as neural networks.
A Survey on Uncertainty Reasoning and Quantification for Decision Making: Belief Theory Meets Deep Learning
We found that only a few studies have leveraged the mature uncertainty research in belief/evidence theories in ML/DL to tackle complex problems under different types of uncertainty.
Searching for Optimal Subword Tokenization in Cross-domain NER
Input distribution shift is one of the vital problems in unsupervised domain adaptation (UDA).
A Neural Corpus Indexer for Document Retrieval
To this end, we propose Neural Corpus Indexer (NCI), a sequence-to-sequence network that generates relevant document identifiers directly for a designated query.
A Knowledge-Enhanced Adversarial Model for Cross-lingual Structured Sentiment Analysis
Notably, we propose a Knowledge-Enhanced Adversarial Model (\texttt{KEAM}) with both implicit distributed and explicit structural knowledge to enhance the cross-lingual transfer.
Enhancing Event-Level Sentiment Analysis with Structured Arguments
Previous studies about event-level sentiment analysis (SA) usually model the event as a topic, a category or target terms, while the structured arguments (e. g., subject, object, time and location) that have potential effects on the sentiment are not well studied.
Dynamic Split Computing for Efficient Deep Edge Intelligence
Split computing is a paradigm where a DNN is split into two sections; the first section is executed on the end device, and the output is transmitted to the edge server where the final section is executed.
Sequential/Session-based Recommendations: Challenges, Approaches, Applications and Opportunities
In recent years, sequential recommender systems (SRSs) and session-based recommender systems (SBRSs) have emerged as a new paradigm of RSs to capture users' short-term but dynamic preferences for enabling more timely and accurate recommendations.
Cross-View Cross-Scene Multi-View Crowd Counting
Multi-view crowd counting has been previously proposed to utilize multi-cameras to extend the field-of-view of a single camera, capturing more people in the scene, and improve counting performance for occluded people or those in low resolution.
Rapid Phase Ambiguity Elimination Methods for DOA Estimator via Hybrid Massive MIMO Receive Array
In the proposed Max-RP-QI, a quadratic interpolation scheme is adopted to interpolate the three DOA values corresponding to the largest three receive powers of Max-RP.
Process Knowledge-infused Learning for Suicidality Assessment on Social Media
Improving the performance and natural language explanations of deep learning algorithms is a priority for adoption by humans in the real world.
Multi-view Information Bottleneck Without Variational Approximation
By "intelligently" fusing the complementary information across different views, multi-view learning is able to improve the performance of classification tasks.
A Benchmark for Automatic Medical Consultation System: Frameworks, Tasks and Datasets
In recent years, interest has arisen in using machine learning to improve the efficiency of automatic medical consultation and enhance patient experience.
MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective
NER model has achieved promising performance on standard NER benchmarks.
Ranked #8 on
Named Entity Recognition (NER)
on WNUT 2017
PixelFolder: An Efficient Progressive Pixel Synthesis Network for Image Generation
Pixel synthesis is a promising research paradigm for image generation, which can well exploit pixel-wise prior knowledge for generation.
Stereo Unstructured Magnification: Multiple Homography Image for View Synthesis
A two-stage network is developed for novel view synthesis.
Distill-VQ: Learning Retrieval Oriented Vector Quantization By Distilling Knowledge from Dense Embeddings
We perform comprehensive explorations for the optimal conduct of knowledge distillation, which may provide useful insights for the learning of VQ based ANN index.
CMMD: Cross-Metric Multi-Dimensional Root Cause Analysis
To this end, we propose a cross-metric multi-dimensional root cause analysis method, named CMMD, which consists of two key components: 1) relationship modeling, which utilizes graph neural network (GNN) to model the unknown complex calculation among metrics and aggregation function among dimensions from historical data; 2) root cause localization, which adopts the genetic algorithm to efficiently and effectively dive into the raw data and localize the abnormal dimension(s) once the KPI anomalies are detected.
UV Volumes for Real-time Rendering of Editable Free-view Human Performance
Neural volume rendering enables photo-realistic renderings of a human performer in free-view, a critical task in immersive VR/AR applications.
Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap
Our theory suggests an alternative understanding of contrastive learning: the role of aligning positive samples is more like a surrogate task than an ultimate goal, and the overlapped augmented views (i. e., the chaos) create a ladder for contrastive learning to gradually learn class-separated representations.
PEAR: Personalized Re-ranking with Contextualized Transformer for Recommendation
Specifically, PEAR not only captures feature-level and item-level interactions, but also models item contexts from both the initial ranking list and the historical clicked item list.
Divide and Conquer: Text Semantic Matching with Disentangled Keywords and Intents
Text semantic matching is a fundamental task that has been widely used in various scenarios, such as community question answering, information retrieval, and recommendation.
An Effective Way for Cross-Market Recommendation with Hybrid Pre-Ranking and Ranking Models
The Cross-Market Recommendation task of WSDM CUP 2022 is about finding solutions to improve individual recommendation systems in resource-scarce target markets by leveraging data from similar high-resource source markets.
Bayesian Sequential Stacking Algorithm for Concurrently Designing Molecules and Synthetic Reaction Networks
The design variables consist of a set of reactants in a reaction network and its network topology.
Communication-Efficient Actor-Critic Methods for Homogeneous Markov Games
Recent success in cooperative multi-agent reinforcement learning (MARL) relies on centralized training and policy sharing.
HousE: Knowledge Graph Embedding with Householder Parameterization
The effectiveness of knowledge graph embedding (KGE) largely depends on the ability to model intrinsic relation patterns and mapping properties.
Decorrelate Irrelevant, Purify Relevant: Overcome Textual Spurious Correlations from a Feature Perspective
Most of the existing debiasing methods often identify and weaken these samples with biased features (i. e., superficial surface features that cause such spurious correlations).
Post-Training Quantization for Cross-Platform Learned Image Compression
It has been witnessed that learned image compression has outperformed conventional image coding techniques and tends to be practical in industrial applications.
Uni-Retriever: Towards Learning The Unified Embedding Based Retriever in Bing Sponsored Search
On the other hand, the capability of making high-CTR retrieval is optimized by learning to discriminate user's clicked ads from the entire corpus.
Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based Retrieval
In this work, we tackle this problem with Bi-Granular Document Representation, where the lightweight sparse embeddings are indexed and standby in memory for coarse-grained candidate search, and the heavyweight dense embeddings are hosted in disk for fine-grained post verification.
PromptBERT: Improving BERT Sentence Embeddings with Prompts
We propose PromptBERT, a novel contrastive learning method for learning better sentence representation.
A Multi-agent Reinforcement Learning Approach for Efficient Client Selection in Federated Learning
Federated learning (FL) is a training technique that enables client devices to jointly learn a shared model by aggregating locally-computed models without exposing their raw data.
Hallucinated Neural Radiance Fields in the Wild
This paper studies the problem of hallucinated NeRF: i. e., recovering a realistic NeRF at a different time of day from a group of tourism images.
FENeRF: Face Editing in Neural Radiance Fields
2D GANs can generate high fidelity portraits but with low view consistency.
HDR-NeRF: High Dynamic Range Neural Radiance Fields
The key to our method is to model the physical imaging process, which dictates that the radiance of a scene point transforms to a pixel value in the LDR image with two implicit functions: a radiance field and a tone mapper.
Deblur-NeRF: Neural Radiance Fields from Blurry Images
We demonstrate that our method can be used on both camera motion blur and defocus blur: the two most common types of blur in real scenes.
MQBench: Towards Reproducible and Deployable Model Quantization Benchmark
Surprisingly, no existing algorithm wins every challenge in MQBench, and we hope this work could inspire future research directions.
Learning Implicit Sentiment in Aspect-based Sentiment Analysis with Supervised Contrastive Pre-Training
Aspect-based sentiment analysis aims to identify the sentiment polarity of a specific aspect in product reviews.
