1
KLUE: Korean Language Understanding Evaluation
2
PanGu-α: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation
3
Carbon Emissions and Large Neural Network Training
4
The Power of Scale for Parameter-Efficient Prompt Tuning
5
GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation
6
Generating Datasets with Pretrained Language Models
7
Retrieval Augmentation Reduces Hallucination in Conversation
8
Rainbow Memory: Continual Learning with a Memory of Diverse Samples
9
On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜
10
A Survey on Bias in Deep NLP
11
Calibrate Before Use: Improving Few-Shot Performance of Language Models
12
Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm
13
Understanding the Capabilities, Limitations, and Societal Impact of Large Language Models
14
What Makes Good In-Context Examples for GPT-3?
15
Persistent Anti-Muslim Bias in Large Language Models
16
WARP: Word-level Adversarial ReProgramming
17
Do Neural Language Models Overcome Reporting Bias?
18
mT5: A Massively Multilingual Pre-trained Text-to-Text Transformer
19
An Empirical Study of Tokenization Strategies for Various Korean NLP Tasks
20
Controlling Style in Generated Dialogue
21
It’s Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners
22
Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering
23
Tangled up in BLEU: Reevaluating the Evaluation of Automatic Machine Translation Evaluation Metrics
24
Language Models are Few-Shot Learners
25
Recipes for Building an Open-Domain Chatbot
26
PhoBERT: Pre-trained language models for Vietnamese
27
Towards a Human-like Open-Domain Chatbot
28
Scaling Laws for Neural Language Models
29
RobBERT: a Dutch RoBERTa-based Language Model
30
CamemBERT: a Tasty French Language Model
31
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
32
Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism
33
KorQuAD1.0: Korean QA Dataset for Machine Reading Comprehension
34
CTRL: A Conditional Transformer Language Model for Controllable Generation
35
Poly-encoders: Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring
36
Multi-Modal Generative Adversarial Network for Short Product Title Generation in Mobile E-Commerce
37
SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing
38
Decoupled Weight Decay Regularization
39
SQuAD: 100,000+ Questions for Machine Comprehension of Text
40
Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
41
Prefix-Tuning: Optimizing Continuous Prompts for Generation
42
PADA: A Prompt-based Autoregressive Approach for Adaptation to Unseen Domains
43
McMillanMajor, and Shmargaret Shmitchell
44
Keywords: slippers, indoor slippers, office slippers, high heels, spring new arrival shoes, spring shoes, women’s slippers, female slippers, women’s high heels, female high heels
45
Knowledge distillation for lightweight roberta of korean
46
AutoPrompt: Eliciting knowledge from language models with automatically generated prompts
47
Korean, English, Japanese, and other languages, respectively. A.2 Data Cleaning In a similar way to the work
48
Keywords: imported bowl, vintage bowl, enamel pot, spoon and chopsticks set, strong cup, retro pot 날
49
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
50
Language Models are Unsupervised Multitask Learners
51
Chatbot personalities matters
52
Title: Spring women’s office slippers high heels SALE
53
We introduce HyperCLOVA, a large-scale Korean in-context learning-based LM with nearly 100B parameters, by constructing a large Korean-centric corpus of 560B tokens
54
Title: White Day Couple Jewelry Sale
55
Title: Kitchenware overseas direct purchase discount exhibition
56
We discover the effect of language-specific tokenization on large-scale in-context LMs for training corpus of non-English languages
