Simple vector space model retrieval system

Normalize emphasized words

Creates output files containing word counts and P.O.S. Tag distribution using Stanford's Core NLP library

An HTTP API for TermSuite

A search engine to index and query documents

一个基于HanLP的分词工具

Gachon University, Korea - Dept of software - Graduation Project

SDK and example code for building voice-enabled skills for the Amazon Echo.

The IK Analysis plugin integrates Lucene IK analyzer into elasticsearch, support customized dictionary.

中文自然语言处理工具包 Toolkit for Chinese natural language processing

In this project, we try to reproduce the paper 'Comparing Measures of Semantic Similarity' by Nikola Ljubešić et al. which aims at comparing different methods for automatic extraction of semantic similarity mesaures from a corpus.

This implements the Viterbi Algorithm in Java for Parts of Speech Tagging, generating a comprehensive accuracy and F1 score.

My legal background gave me a deep appreciation for language's importance. It's not just words; it's a profound understanding woven into every case. This connection led me to coding, where I coded a potent pipeline system with Stanford CoreNLP.

Speech-Emotion-Recognition-app

This project illustrates using https://api.ai/ for enabling rich conversation in Russian.

A modified version of the Stanford CoreNLP full 3.6.0, in which the machine reading classes for Relation Extraction now support extra parameters for definitions of custom NER entities.

A multiclass-perceptron based Part-of-Speech tagger

A machine learning tool for fishing entities