Seminar > Paper Reviews

논문 제목

Effective Sequence-to-Sequence Dialogue State Tracking  

DeBERTa: Decoding-Enhanced BERT with Dis-Entangled Attention 

KorNLI and KorSTS - New Benchmark Datasets Korean Natural Language Understanding 

Long-Span Summarization via Local Attention and Content Selection 

An Ensemble Model for Fake Online Review Detection Based on Data Resampling, Feature Pruning, and Parameter Optimization 

Document Modeling with External Attention for Sentence Extraction

Towards Universal Dialogue State Tracking

KR-BERT: A Small-Scale Korean-Specific Language Model

Longformer: The Long-Document Transformer 

PMI-MASKING: PRINCIPLED MASKING OF CORRELATED SPANS 

Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems 

COVID-Fact Fact Extraction and Verification of Real-World Claims on COVID-19 Pandemic 

Hi-Transformer: Hierarchical Interactive Transformer for Efficient and Effective Long Document Modeling 

Data Augmentation Using Pre-trained Transformer Models 

HIBERT Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization