Seminar > Paper Reviews

논문 제목

Don't Stop Pretraining: Adapt Language Models to Domains and Tasks 

정보과학회 리뷰

A Hybrid Neural Network Model for Commonsense Reasoning

Reference and document aware semantic evaluation methods for korean language summarization

Multimodal Transformer for Unaligned Multimodal Language Sequences 

BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension

SummCoder: An unsupervised framework for extractive text summarization based on deep auto-encoders 

SSMix: Saliency-Based Span Mixup for Text Classification 

PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization

Exploring Neural Text Simplification Models 

DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter 

Learning Loss for Active Learning, CVPR2019 

Bertscore: Evaluating text generation with bert 

Conditional Neural Generation using Sub-Aspect Functions for Extractive News Summarization 

ELECTRA: PRE-TRAINING TEXT ENCODERS AS DISCRIMINATORS RATHER THAN GENERATORS 

CombiNMT-An Exploration into Neural Text Simplification

An Empirical Study of Tokenization Strategies for Various Korean NLP Tasks