girlgunner

leadlda

This project includes the codes and data for our LeadLDA model targeting to extract topics from short and colloquial microblog messages. More details can be found in our paper published in ACL 2016 titled as "Topic Extraction from Microblog Posts Using Conversation Structures".

ansj_seg

ansj分词.ict的真正java实现.分词效果速度都超过开源版的ict. 中文分词,人名识别,词性标注,用户自定义词典

fnlp

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

JASCM

jingli

LDAGibbsSampling

Liu Yang's implementation for Gibbs Sampling of LDA

ROUGE-2.0

Java implementation of ROUGE for evaluation of summarization tasks. Stemming, stopwords and unicode support.

SC-GPT

Few-shot Natural Language Generation for Task-Oriented Dialog

summarizer

UNMAINTAINED: A multidocument text summarizer, the final project for CIS-530: Intro to Computational Linguistics

TAKG

The official implementation of ACL 2019 paper "Topic-Aware Neural Keyphrase Generation for Social Media Language"

TMN

Source code of TMN (Topic Memory Network)

Topic_Disc

Source code and dataset of "Joint Modeling of Topics and Discourse in Microblog Conversations"

Twitter-LDA

Latent Dirichlet Allocation (LDA) model for Microblogs (Twitter, weibo etc.)