Masatoshi Suzuki

WikiEntVec. Distributed representations of words and named entities trained on Wikipedia.

wikipedia-utils. Utility scripts for preprocessing Wikipedia texts for NLP

japanese-bert. BERT models with tokenization for Japanese texts.

WikiCleaner. Python

aio2-soseki-baseline. Baseline QA system for AIO2 competition utilizing BPR (binary passage retrieval)

aio2-tfidf-baseline. TFIDF-based QA system for AIO2 competition

wikipedia-paragraphs. Cleaned Wikipedia paragraphs for natural language processing (NLP)

TypedKB. Fine-grained named entity classification of Wikipedia articles.

closed-book-qa. Quizbowl as a testbed of entity knowledge