Leveraging BERT and c-TF-IDF to create easily interpretable topics.

微博超级话题爬虫，微博词频统计+情感分析+简单分类，新增肺炎超话爬取数据

Code for EMNLP 2021 paper "Topic-Aware Contrastive Learning for Abstractive Dialogue Summarization"

IEML semantic language - a meaning-representation system based on semantic primitives and a regular grammar. Basic semantic relationships between concepts are automatically computed from syntactic similarities.

Implementation of EMNLP2020 accepted paper: "TopicBERT: Topic-aware BERT for Efficient Document Classification"

The monitoring tool helps to analyse and monitor ROS Systems

Python script demonstrating spark streaming and Kafka implementation using an e-commerce website like product recommendation engine based on item-based collaborative filtering. 🐍. 💥

A pub/sub architecture genetically engineered to make your project simpler, not more complicated. And to be adorable.

It will take backup of given topic and store that into either local filesystem or S3.It will also restore from given local filesystem or S3.

Topic Embedding, Text Generation and Modeling using diffusion

NLP on Korean news articles. Automatic topic extraction through dynamic clustering.

Semi supervised Topic Modeling using Neural Network

函数流，数据流，同步异步，事件驱动，多种模式channel

Quality Metrics for Topic Modeling

This system evaluates a collection of mementos (archived web pages) to determine which are off topic. The collection can be part of an Archive-It collection, a single TimeMap, or stored in a WARC file.

A Bayesian Multilingual Document Model

My Graduation Project for Faculty of Computers and Information, Helwan Univeristy, Computer Science Department

Web crawler for collecting Facebook feeds using a keyword

Social feed aggregation service, written in Django

Aiven Kafka Restore Utility