Model

RNN, LSTM, GRU

Sequence to Sequence with Attention

Transformer

[BERT, GPT]Self-supervised Pre-training Models

ETC

pad_seqence / pack_sequence

BPTT

Word Representation

Decoding of Language Model(1)

Decoding of Language Model(2)

NLP Metrics

Paper

An Improved Baseline for Sentence-level Relation Extraction 리뷰

Questions

Comparison of Embedding Layer and Pretrained Word Embedding