Resources

Corpus

• sscorpus: A monolingual parallel corpus for sentence simplification

• TMU Japanese Twitter Corpus

• Tokyo Metropolitan University Paraphrase Corpus (TMUP)

Dictionary

• Simple PPDB: Japanese

• MIPA: Mutual Information Based Paraphrase Acquisition via Bilingual Pivoting

Evaluation data

• • TMU Japanese Lexical Simplification Dataset

  • TMU Japanese Compound Verb Paraphrase Dataset

• TMU Japanese Word Similarity Dataset

Misc Data

• English Spelling Error Log Extracted from an English Word Typing Game

Demo

• • Tokyo Metropolitan University Japanese-English Neural Machine Translation (WAT 2017)

  • English Grammatical Error Detection (IJCNLP 2017)

  • Japanese Sentiment Classifier with Deep Learning (PACLIC 2015)

Tool

• • Neural Machine Translation (WAT 2016)

  • Grammatical Error Detection (IJCNLP 2017)

• Distant Term Extractor

• RUSE: Regression model Using Sentence Embeddings for Automatic Machine Translation Evaluation (WMT 2018)