mrmiywj/CS332-SJTU

Internet-based Information Extraction Technologies, project Specific Relation Extraction

The project for CS332 in SJTU. In progress:

1. Read corpus from file
2. Word segmentation
3. Generate word vector
4. POS
5. Name Entity Recognization

NOTE: Some word not in model will be mark nas None in word vectors

Platform:

1. Word2Vec, gensim, model: https://github.com/to-shimo/chinese-word2vec
2. Pyltp: https://github.com/HIT-SCIR/pyltp

Usage: Install the libs, download models to this repo.