Stars
今日头条中文新闻(文本)分类数据集
A concept and obvious expression pattern collection of Chinese compound event extraction which then be evolved into ComplexEventGraph,本项目提出了中文复合事件的概念与显式模式,包括条件事件、因果事件、顺承事件、反转事件等事件抽取,并形成事理图谱。
Python implemetation for Dirichlet Multinomial Mixture (DMM) model
Machine Learning / Natural Language Processing / Information Retrieval
thomsonreuters / attr2vec
Forked from geffy/tffmTensorFlow implementation of an arbitrary order Factorization Machine
A demo code for topical word embedding
Dynamic Meta-Embeddings for Improved Sentence Representations
Package for evaluating word embeddings
Code for COLING 2018 paper Learning Word Meta-Embeddings by Autoencoding
Topic modeling with latent Dirichlet allocation using Gibbs sampling
一个生产级、高性能、模块化、可扩展的中文NLP工具包。(中文分词、平均感知机、fastText、拼音、新词发现、分词纠错、BM25、人名识别、命名实体、自定义词典)
Text classifier for Hierarchical Attention Networks for Document Classification
Visualization for simple attention and Google's multi-head attention.
Loading the model from glove and computer word similarity & word clustering.
Topic Modeling for Short Texts with Auxiliary Word Embeddings