austen-w Goto Github PK

bert

使用BERT做文本相似度

financial-knowledge-graphs

小型金融知识图谱构建流程

nlpir

nltk_data

NLTK Data

pdffigures2

Given a scholarly PDF, extract figures, tables, captions, and section titles.

splitwordsdemo

This is a demo created for the summer project in 2018 to split words.

textanalyzer

A text analyzer which is based on machine learning,statistics and dictionaries that can analyze text. So far, it supports hot word extracting, text classification, part of speech tagging, named entity recognition, chinese word segment, extracting address, synonym, text clustering, word2vec model, edit distance, chinese word segment, sentence similarity,word sentiment tendency, name recognition, idiom recognition, placename recognition, organization recognition, traditional chinese recognition, pinyin transform.

tianlianganalyzer

mavent版天亮分词器，基于trie树结构一个分词组件，对词典有一定的依赖性，对“纯字母”、“纯数字”的字符串截断式匹配有过滤功能

trec_news-track