Masato Hagiwara

In this post, I'm going to summarize the Education×NLP papers presented at NAACL 2021 which was hosted online last week. Topics range from grammatical error correction to prerequisite relation extraction.

We are happy to announce GrammarTagger, an open-source toolkit for grammatical profiling for language learning. It can analyze text in English and Chinese and show you grammatical items included in the input, along with its estimated difficulty.

In deep natural language processing (NLP), the input text is often broken into "subword"—units that are shorter than words. In this article, we'll review common subword tokenization techniques including WordPiece, byte-pair encoding (BPE), and SentencePiece,

Pretrained language models (PLMs) such as BERT are used for solving more and more NLP applications in many languages, including Japanese. In this post, I'm going to compare various Japanese pretrained BERT models and their task performance and make a specific recommendation as of this writing.

Automated essay scoring (AES), where a computer algorithm scores student essays automatically, is an important application of natural language processing for education and language learning. In this article, we'll review some of the recent advances in automated essay scoring.