Search Results for author:
Found 47 papers, 21 papers with code
基于抽象语义表示的汉语疑问句的标注与分析(Chinese Interrogative Sentences Annotation and Analysis Based on the Abstract Meaning Representation)
疑问句的句法语义分析在搜索引擎、信息抽取和问答系统等领域有着广泛的应用。计算语言学多采取问句分类和句法分析相结合的方式来处理疑问句, 精度和效率还不理想。而疑问句的语言学研究成果丰富, 比如疑问句的结构类型、疑问焦点和疑问代词的非疑问用法等, 但缺乏系统的形式化表示。本文致力于解决这一难题, 采用基于图结构的汉语句子语义的整体表示方法—中文抽象语义表示(CAMR)来标注疑问句的语义结构, 将疑问焦点和整句语义一体化表示出来。然后选取了宾州中文树库CTB8. 0网络媒体语料、小学语文教材以及《小王子》中文译本的2万句语料中共计2071句疑问句, 统计了疑问句的主要特点。统计表明, 各种疑问代词都可以通过疑问概念amr-unknown和语义关系的组合来表示, 能够完整地表示出疑问句的关键信息、疑问焦点和语义结构。最后, 根据疑问代词所关联的语义关系, 统计了疑问焦点的概率分布, 其中原因、修饰语和受事的占比最高, 分别占26. 53%、16. 73%以及16. 44%。基于抽象语义表示的疑问句标注与分析可以为汉语疑问句研究提供基础理论与资源。
Adaptive Sampled Softmax with Inverted Multi-Index: Methods, Theory and Applications
The softmax function is a cornerstone of multi-class classification, integral to a wide range of machine learning applications, from large-scale retrieval and ranking models to advanced large language models.
DeepSeek-V3 Technical Report
We present DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
Enhancing Low Dose Computed Tomography Images Using Consistency Training Techniques
This is combined with a sinusoidal curriculum that enhances the learning of the trajectory between the noise distribution and the posterior distribution of interest, allowing High Noise Improved Consistency Training (HN-iCT) to be trained in a supervised fashion.
Multiscale Latent Diffusion Model for Enhanced Feature Extraction from Medical Images
In response to these challenges, we propose LTDiff++, a multiscale latent diffusion model designed to enhance feature extraction in medical imaging.
Trusted Unified Feature-Neighborhood Dynamics for Multi-View Classification
This method effectively integrates local and global feature-neighborhood (F-N) structures for robust decision-making.
Efficient Transfer Learning Framework for Cross-Domain Click-Through Rate Prediction
The challenges include the inefficiencies arising from the management of extensive source data and the problem of 'catastrophic forgetting' that results from the CTR model's daily updating.
Beyond Uncertainty: Evidential Deep Learning for Robust Video Temporal Grounding
To the best of our knowledge, this marks the first successful attempt of DER in VTG.
Dual Test-time Training for Out-of-distribution Recommender System
To address this challenge, we propose a novel Dual Test-Time-Training framework for OOD Recommendation, termed DT3OR.
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
MLA guarantees efficient inference through significantly compressing the Key-Value (KV) cache into a latent vector, while DeepSeekMoE enables training strong models at an economical cost through sparse computation.
ChangeAnywhere: Sample Generation for Remote Sensing Change Detection via Semantic Latent Diffusion Model
Remote sensing change detection (CD) is a pivotal technique that pinpoints changes on a global scale based on multi-temporal images.
High Noise Scheduling is a Must
The results show that the polynomial noise distribution outperforms the model trained with log-normal noise distribution, yielding a 33. 54 FID score after 100, 000 training steps with constant discretization steps.
Text2MDT: Extracting Medical Decision Trees from Medical Texts
In this work, we propose a novel task, Text2MDT, to explore the automatic extraction of MDTs from medical texts such as medical guidelines and textbooks.
An Incremental Update Framework for Online Recommenders with Data-Driven Prior
To address the aforementioned issue, we propose an incremental update framework for online recommenders with Data-Driven Prior (DDP), which is composed of Feature Prior (FP) and Model Prior (MP).
Scaling up the formation of agents with heterogeneous sensing: mixed distance and bearing-only
Unlike the case with identical neighboring agents whose actions are mirrored, the problem of distributed formation control design with heterogeneous sensing is not straightforward.
Deep Group Interest Modeling of Full Lifelong User Behaviors for CTR Prediction
The insights from this subset reveal the user's decision-making process related to the candidate item, improving prediction accuracy.
Batch-Mix Negative Sampling for Learning Recommendation Retrievers
Recommendation retrievers commonly retrieve user potentially preferred items from numerous items, where the query and item representation are learned according to the dual encoders with the log-softmax loss.
Latent Diffusion Model for Medical Image Standardization and Enhancement
Finally, the decoder uses the transformed latent representation to generate a standardized CT image, providing a more consistent basis for downstream analysis.
When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunities
The advent of large language models marks a revolutionary breakthrough in artificial intelligence.
Human-annotated label noise and their impact on ConvNets for remote sensing image scene classification
However, the distribution of real-world human-annotated label noises on remote sensing images and their impact on ConvNets have not been investigated.
Forward-Forward Contrastive Learning
Medical image classification is one of the most important tasks for computer-aided diagnosis.
Meta-causal Learning for Single Domain Generalization
Under this paradigm, we propose a meta-causal learning method to learn meta-knowledge, that is, how to infer the causes of domain shift between the auxiliary and source domains during training.
Ranked #2 on
Single-Source Domain Generalization
on PACS
DiffusionCT: Latent Diffusion Model for CT Image Standardization
This work addresses the issue of CT image harmonization using a new diffusion-based model, named DiffusionCT, to standardize CT images acquired from different vendors and protocols.
SoccerNet 2022 Challenges Results
The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team.
Bootstrap Generalization Ability from Loss Landscape Perspective
Domain generalization aims to learn a model that can generalize well on the unseen test dataset, i. e., out-of-distribution data, which has different distribution from the training dataset.
Cooperative Retriever and Ranker in Deep Recommenders
Deep recommender systems (DRS) are intensively applied in modern web services.
Cache-Augmented Inbatch Importance Resampling for Training Recommender Retriever
Recommender retrievers aim to rapidly retrieve a fraction of items from the entire item corpus when a user query requests, with the representative two-tower model trained with the log softmax loss.
Cross-Vendor CT Image Data Harmonization Using CVH-CT
We propose a novel deep learning approach called CVH-CT for harmonizing CT images captured using scanners from different vendors.
Fast Variational AutoEncoder with Inverted Multi-Index for Collaborative Filtering
Variational AutoEncoder (VAE) has been extended as a representative nonlinear method for collaborative filtering.
Learning 3D Mineral Prospectivity from 3D Geological Models Using Convolutional Neural Networks: Application to a Structure-controlled Hydrothermal Gold Deposit
The three-dimensional (3D) geological models are the typical and key data source in the 3D mineral prospecitivity modeling.
CT Image Harmonization for Enhancing Radiomics Studies
While remarkable advances have been made in Computed Tomography (CT), capturing CT images with non-standardized protocols causes low reproducibility regarding radiomic features, forming a barrier on CT image analysis in a large scale.
Predicting Opioid Use Disorder from Longitudinal Healthcare Data using Multi-stream Transformer
Opioid Use Disorder (OUD) is a public health crisis costing the US billions of dollars annually in healthcare, lost workplace productivity, and crime.
Fibre-base duality of 5d KK theories
We study circle compactifications of 6d superconformal field theories giving rise to 5d rank 1 and rank 2 Kaluza-Klein theories.
High Energy Physics - Theory
FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery
In this paper, we propose a novel benchmark dataset with more than 1 million instances and more than 15, 000 images for Fine-grAined object recognItion in high-Resolution remote sensing imagery which is named as FAIR1M.
Efficient Optimal Selection for Composited Advertising Creatives with Tree Structure
Based on the tree structure, Thompson sampling is adapted with dynamic programming, leading to efficient exploration for potential ad creatives with the largest CTR.
Automated Creative Optimization for E-Commerce Advertising
However, interactions between creative elements may be more complex than the inner product, and the FM-estimated CTR may be of high variance due to limited feedback.
ELMV: an Ensemble-Learning Approach for Analyzing Electrical Health Records with Significant Missing Values
We propose a novel Ensemble-Learning for Missing Value (ELMV) framework, which introduces an effective approach to construct multiple subsets of the original EHR data with a much lower missing rate, as well as mobilizing a dedicated support set for the ensemble learning in the purpose of reducing the bias caused by substantial missing values.
STAN-CT: Standardizing CT Image using Generative Adversarial Network
Computed tomography (CT) plays an important role in lung malignancy diagnostics and therapy assessment and facilitating precision medicine delivery.
Dynamic Region-Aware Convolution
More gracefully, our DRConv transfers the increasing channel-wise filters to spatial dimension with learnable instructor, which not only improve representation ability of convolution, but also maintains computational cost and the translation-invariance as standard convolution dose.
Ranked #19 on
Semantic Segmentation
on MCubeS
Adaptive Graph Convolutional Network with Attention Graph Clustering for Co-saliency Detection
Second, we develop an attention graph clustering algorithm to discriminate the common objects from all the salient foreground objects in an unsupervised fashion.
Video Saliency Prediction Using Enhanced Spatiotemporal Alignment Network
Due to a variety of motions across different frames, it is highly challenging to learn an effective spatiotemporal representation for accurate video saliency prediction (VSP).
Deep Object Co-segmentation via Spatial-Semantic Network Modulation
With the multi-resolution features of the relevant images as input, we design a spatial modulator to learn a mask for each image.
Erroneous data generation for Grammatical Error Correction
It has been demonstrated that the utilization of a monolingual corpus in neural Grammatical Error Correction (GEC) systems can significantly improve the system performance.
DeepAAA: clinically applicable and generalizable detection of abdominal aortic aneurysm using deep learning
We find that DeepAAA exceeds literature-reported performance of radiologists on incidental AAA detection.
Domain Adversarial Reinforcement Learning for Partial Domain Adaptation
In this more general and practical scenario, a major challenge is how to select source instances in the shared classes across different domains for positive transfer.
CLUF: a Neural Model for Second Language Acquisition Modeling
Second Language Acquisition Modeling is the task to predict whether a second language learner would respond correctly in future exercises based on their learning history.
Joint Multi-Leaf Segmentation, Alignment and Tracking from Fluorescence Plant Videos
First, leaf segmentation and alignment are applied on the last frame of a plant video to find a number of well-aligned leaf candidates.
