Search Results for author:
Found 30 papers, 12 papers with code
Reconciling Shared versus Context-Specific Information in a Neural Network Model of Latent Causes
Through learning, it naturally stores structure that is shared across tasks in the network weights.
How should the advent of large language models affect the practice of science?
For this opinion piece, we have invited four diverse groups of scientists to reflect on this query, sharing their perspectives and engaging in debate.
Forgettable Federated Linear Learning with Certified Data Removal
To this end, we propose the Forgettable Federated Linear Learning (2F2L) framework featured with novel training and data removal strategies.
FedMT: Federated Learning with Mixed-type Labels
In federated learning (FL), classifiers (e. g., deep networks) are trained on datasets from multiple data centers without exchanging data across them, which improves the sample efficiency.
Reinforced Structured State-Evolution for Vision-Language Navigation
However, the crucial navigation clues (i. e., object-level environment layout) for embodied navigation task is discarded since the maintained vector is essentially unstructured.
Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencoder
State of the art (SOTA) few-shot learning (FSL) methods suffer significant performance drop in the presence of domain differences between source and target datasets.
Minimum Wasserstein Distance Estimator under Finite Location-scale Mixtures
Do we gain anything by learning finite location-scale mixtures via a minimum Wasserstein distance estimator (MWDE)?
Room-and-Object Aware Knowledge Reasoning for Remote Embodied Referring Expression
The Remote Embodied Referring Expression (REVERIE) is a recently raised task that requires an agent to navigate to and localise a referred remote object according to a high-level language instruction.
Classification Beats Regression: Counting of Cells from Greyscale Microscopic Images based on Annotation-free Training Samples
Modern methods often formulate the counting of cells from microscopic images as a regression problem and more or less rely on expensive, manually annotated training images (e. g., dot annotations indicating the centroids of cells or segmentation masks identifying the contours of cells).
Distributed Learning of Finite Gaussian Mixtures
Experiments based on simulated and real-world data show that the proposed split-and-conquer approach has comparable statistical performance with the global estimator based on the full dataset, if the latter is feasible.
SemEval-2020 Task 5: Counterfactual Recognition
Subtask-1 aims to determine whether a given sentence is a counterfactual statement or not.
Camouflaged Chinese Spam Content Detection with Semi-supervised Generative Active Learning
We propose a Semi-supervIsed GeNerative Active Learning (SIGNAL) model to address the imbalance, efficiency, and text camouflage problems of Chinese text spam detection task.
Robust Layout-aware IE for Visually Rich Documents with Pre-trained Language Models
Many business documents processed in modern NLP and IR pipelines are visually rich: in addition to text, their semantics can also be captured by visual traits such as layout, format, and fonts.
Network Embedding Using Deep Robust Nonnegative Matrix Factorization
Extensive experiments on several benchmarks of complex networks demonstrate that our proposed method DRNMF is effective and has better performance than the state-of-the-art matrix factorization based methods for network embedding.
Masking Orchestration: Multi-task Pretraining for Multi-role Dialogue Representation Learning
Multi-role dialogue understanding comprises a wide range of diverse tasks such as question answering, act classification, dialogue summarization etc.
Gaussian Mixture Reduction with Composite Transportation Divergence
Although existing clustering-based methods are known for their satisfactory performance and computational efficiency, their convergence properties and optimal targets remain unknown.
Rumor Detection on Social Media: Datasets, Methods and Opportunities
Social media platforms have been used for information and news gathering, and they are very valuable in many applications.
Review-based Question Generation with Adaptive Instance Transfer and Augmentation
We propose an iterative learning framework for handling this challenge via adaptive transfer and augmentation of the training instances with the help of the available user-posed question-answer data.
Uncover Sexual Harassment Patterns from Personal Stories by Joint Key Element Extraction and Categorization
Sexual harassment occurred in a variety of situations, and categorization of the stories and extraction of their key elements will provide great help for the related parties to understand and address sexual harassment.
Using Customer Service Dialogues for Satisfaction Analysis with Context-Assisted Multiple Instance Learning
Customers ask questions and customer service staffs answer their questions, which is the basic service model via multi-turn customer service (CS) dialogues on E-commerce platforms.
Detect Camouflaged Spam Content via StoneSkipping: Graph and Text Joint Embedding for Chinese Character Variation Representation
The VFGE can learn both the graph embeddings of the Chinese characters (local) and the latent variation families (global).
Ranked #1 on
Chinese Spam Detection
on SMS
Rumor Detection by Exploiting User Credibility Information, Attention and Multi-task Learning
In this study, we propose a new multi-task learning approach for rumor detection and stance classification tasks.
eventAI at SemEval-2019 Task 7: Rumor Detection on Social Media by Exploiting Content, User Credibility and Propagation Information
This paper describes our system for SemEval 2019 RumorEval: Determining rumor veracity and support for rumors (SemEval 2019 Task 7).
Graph Convolution for Multimodal Information Extraction from Visually Rich Documents
In VRDs, visual and layout information is critical for document understanding, and texts in such documents cannot be serialized into the one-dimensional sequence without losing information.
Multi-Instance Learning for End-to-End Knowledge Base Question Answering
This paper proposes a novel approach based on multiple instance learning to address the problem of noisy answers by exploring consensus among answers to the same question in training end-to-end KBQA models.
Knowledge Base Question Answering
Multiple Instance Learning
Improving Distantly Supervised Relation Extraction with Neural Noise Converter and Conditional Optimal Selector
Distant supervised relation extraction has been successfully applied to large corpus with thousands of relations.
Improve Neural Entity Recognition via Multi-Task Data Selection and Constrained Decoding
Entity recognition is a widely benchmarked task in natural language processing due to its massive applications.
Aurora: Providing Trusted System Services for Enclaves On an Untrusted System
Intel SGX provisions shielded executions for security-sensitive computation, but lacks support for trusted system services (TSS), such as clock, network and filesystem.
Cryptography and Security
Generating Handwritten Chinese Characters using CycleGAN
Our method is applied not only to commonly used Chinese characters but also to calligraphy work with aesthetic values.
Recommending Complementary Products in E-Commerce Push Notifications with a Mixture Model Approach
The item with the highest predicted open rate is then chosen to be included in the push notification message for each user.
