This repository contains a dataset for semantically appropriate application of lexical constraints in NMT.

Python API for Kiwi

The code and models for "An Empirical Study of Tokenization Strategies for Various Korean NLP Tasks" (AACL-IJCNLP 2020)

This repository contains the code for "BERTRAM: Improved Word Embeddings Have Big Impact on Contextualized Representations".

BERTScore for Korean

Korean corpus repository