Thông tin nhà nghiên cứu KH&CN

Multilingual SubEvent Relation Extraction: A Novel Dataset and Structure Induction Method

Selecting Optimal Context Sentences for Event-Event Relation Extraction

Unsupervised Domain Adaptation for Text Classification via Meta Self-Paced Learning

Reducing catastrophic forgetting in neural networks via Gaussian mixture approximation

Auxiliary Local Variables for Improving Regularization/prior Approach in Continual Learning

A Spectral Viewpoint on Continual Relation Extraction

Retrieving Relevant Context to Align Representations for Cross-lingual Event Detection

Hierarchical Selection of Important Context for Generative Event Causality Identification with Optimal Transports.

Mixture of experts meets prompt-based continual learning

NeuroMax: Enhancing Neural Topic Modeling via Maximizing Mutual Information and Group Topic Regularization

Preserving Generalization of Language models in Few-shot Continual Relation Extraction

Lifelong Event Detection via Optimal Transport

SharpSeq: Empowering Continual Event Detection through Sharpness-Aware Sequential-task Learning

Realistic Evaluation of Toxicity in Large Language Models

Continual Relation Extraction via Sequential Multi-task Learning

Sharpness-Aware Minimization for Topic Models with High-Quality Document Representations

Mutual-pairing Data Augmentation for Fewshot Continual Relation Extraction

Improving Vietnamese-English Cross-Lingual Retrieval for Legal and General Domain

Enhancing Discriminative Representation in Similar Relation Clusters for Few-Shot Continual Relation Extraction

ToVo: Toxicity Taxonomy via Voting

Adaptive Prompting for Continual Relation Extraction: A Within-Task Variance Perspective

Few-Shot, No Problem: Descriptive Continual Relation Extraction

GloCOM: A Short Text Neural Topic Model via Global Clustering Context

A Framework for Neural Topic Modeling with Mutual Information and Group Regularization

Out-of-vocabulary handling and topic quality control strategies in streaming topic models

Continual variational dropout: a view of auxiliary local variables in continual learning

Balancing stability and plasticity when learning topic models from short and noisy text streams

Adaptive infinite dropout for noisy and sparse data streams

From implicit to explicit feedback: A deep neural network for modeling sequential behaviours and long-short term preferences of online users

Dynamic Transformation of Prior Knowledge Into Bayesian Models for Data Streams

A graph convolutional topic model for short and noisy text streams

Learning hidden chemistry with deep neural networks

Boosting prior knowledge in streaming variational Bayes

Bag of biterms modeling for short texts

Revisiting Supervised Word Embeddings

Neural Poisson Factorization

Eliminating overfitting of probabilistic topic models on short and noisy text: The role of dropout

Employing the Correspondence of Relations and Connectives to Identify Implicit Discourse Relations via Label Embeddings

An Effective NMF-Based Method for Supervised Dimension Reduction

An interpretable method for text summarization based on simplicial non-negative matrix factorization

Effective and Interpretable Document Classification Using Distinctly Labeled Dirichlet Process Mixture Models of von Mises-Fisher Distributions

Enabling Hierarchical Dirichlet Processes to work better for short texts at large scale

Streaming Sentiment-Aspect Analysis

Keeping priors in streaming Bayesian learning

An Effective and Interpretable Method for Document Classification

Collaborative Topic Model for Poisson distributed ratings

Multi-labeled Document Classification using Semi-supervived Mixture Model of Watson distributions on Document Manifold

Document Clustering using Mixture Model of von Mises-Fisher Distributions on Document Manifold

Document classification using semi-supervived mixture model of von Mises-Fisher distributions on document manifold

Document clustering using dirichlet process mixture model of von Mises-Fisher distributions

Improving Vietnamese Web Page Classification by Combining Hybrid Feature Selection and Label Propagation with Link Information

Efficient label propagation for classification on information networks

Các phương pháp suy diễn cho phân tích ngữ nghĩa ẩn trong dữ liệu lớn

Học cách biểu diễn hiệu quả cho ngữ nghĩa ẩn

Khai thác tri thức tiên nghiệm trong mô hình học máy thống kê cho dữ liệu lớn

Tri thức con người trong các mô hình học máy cho dữ liệu lớn hoặc luồng vô hạn

Mô hình ngôn ngữ lớn cho tiếng Việt

Suy diễn các cấu trúc ẩn trong dữ liệu lớn phức tạp

Các phương pháp suy diễn cho phân tích ngữ nghĩa trong dữ liệu lớn

Chú thích ngữ nghĩa cho dữ liệu ảnh và văn bản dựa trên mô hình xác suất.

Chú thích ngữ nghĩa cho dữ liệu ảnh và văn bản dựa trên mô hình xác suất.

Học cách biểu diễn hiệu quả cho ngữ nghĩa ẩn

Khai thác tri thức tiên nghiệm trong mô hình học máy thống kê cho dữ liệu lớn

Mô hình ngôn ngữ lớn cho tiếng Việt

Suy diễn các cấu trúc ẩn trong dữ liệu lớn phức tạp

Tri thức con người trong các mô hình học máy cho dữ liệu lớn hoặc luồng vô hạn