Search Results for author:
Found 19 papers, 7 papers with code
基于多源知识融合的领域情感词典表示学习研究(Domain Sentiment Lexicon Representation Learning Based on Multi-source Knowledge Fusion)
“本文旨在解决领域情感词典构建任务中标注数据资源相对匮乏以及情感语义表示不充分问题, 通过多源数据领域差异计算联合权重, 融合先验情感知识和Fasttext词向量表示学习, 将情感语义知识映射到新的词向量空间, 从无标注数据中自动构建适应大数据多领域和多语言环境的领域情感词典。在中英文多领域公开数据集上的对比实验表明, 与情感词典方法和预训练词向量方法相比, 本文提出的多源知识融合的领域情感词典表示学习方法在实验数据集上的分类正确率均有明显提升, 并在多种算法、多语言、多领域和多数据集上具有较好的鲁棒性。本文还通过消融实验验证了所提出模型的各个模块在提升情感分类效果中的作用。”
Generating Synthetic Datasets for Few-shot Prompt Tuning
A major limitation of prompt tuning is its dependence on large labeled training datasets.
RevMUX: Data Multiplexing with Reversible Adapters for Efficient LLM Batch Inference
Large language models (LLMs) have brought a great breakthrough to the natural language processing (NLP) community, while leading the challenge of handling concurrent customer queries due to their high throughput demands.
A Survey on Natural Language Counterfactual Generation
Natural language counterfactual generation aims to minimally modify a given text such that the modified text will be classified into a different class.
PairCFR: Enhancing Model Training on Paired Counterfactually Augmented Data through Contrastive Learning
Counterfactually Augmented Data (CAD) involves creating new data samples by applying minimal yet sufficient modifications to flip the label of existing data samples to other classes.
Solving Energy-Independent Density for CT Metal Artifact Reduction via Neural Representation
In this work, we propose Density neural representation (Diner), a novel unsupervised MAR method.
Gradient based Feature Attribution in Explainable AI: A Technical Review
Due to the lack of a rigorous definition of explainable AI (XAI), a plethora of research related to explainability, interpretability, and transparency has been developed to explain and analyze the model from various perspectives.
Generative AI for Synthetic Data Generation: Methods, Challenges and the Future
The recent surge in research focused on generating synthetic data from large language models (LLMs), especially for scenarios with limited data availability, marks a notable shift in Generative Artificial Intelligence (AI).
Training Multimedia Event Extraction With Generated Images and Captions
Contemporary news reporting increasingly features multimedia content, motivating research on multimedia event extraction.
On the Domain Adaptation and Generalization of Pretrained Language Models: A Survey
Recent advances in NLP are brought by a range of large-scale pretrained language models (PLMs).
Improving the Sample Efficiency of Prompt Tuning with Domain Adaptation
Prompt tuning, or the conditioning of a frozen pretrained language model (PLM) with soft prompts learned from data, has demonstrated impressive performance on a wide range of NLP tasks.
A Generic Algorithm for Top-K On-Shelf Utility Mining
Compared with traditional utility mining, OSUM can find more practical and meaningful patterns in real-life applications.
A mechanistic-based data-driven approach to accelerate structural topology optimization through finite element convolutional neural network (FE-CNN)
During offline training, a mapping function is built between high and low resolution representations of a given design domain.
Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection
The existence of multiple datasets for sarcasm detection prompts us to apply transfer learning to exploit their commonality.
Federated Learning for Personalized Humor Recognition
In this paper, we propose the FedHumor approach for the recognition of humorous content in a personalized manner through Federated Learning (FL).
DIFER: Differentiable Automated Feature Engineering
Extensive experiments on classification and regression datasets demonstrate that DIFER can significantly improve the performance of various machine learning algorithms and outperform current state-of-the-art AutoFE methods in terms of both efficiency and performance.
False Discovery Rate Control Under General Dependence By Symmetrized Data Aggregation
We develop a new class of distribution--free multiple testing rules for false discovery rate (FDR) control under general dependence.
Methodology Statistics Theory Statistics Theory
Deep Learning Inversion of Electrical Resistivity Data
According to the comprehensive qualitative analysis and quantitative comparison, ERSInvNet with tier feature map, smooth constraints, and depth weighting function together achieve the best performance.
