KoBERTopic은 BERTopic을 한국어 데이터에 적용할 수 있도록 토크나이저와 BERT를 수정한 코드입니다.

HDBSCAN Tuning for BERTopic Models

BERTopic 中文使用範例

We created a topic modeling pipeline to evaluate different topic modeling algorithms, including their performance on short and long text, preprocessed and not preprocessed datasets, and with different embedding models. Finally, we summarized the results and suggested how to choose algorithms based on the task.

Information extraction from unstructured text to build a knowledge graph using techniques from traditional NLP to pre-trained transformers and LLMs for NER and Linking, and Relation Extraction.

Project scripts for network analysis of topics discovered by Math Research Compass

LLM-adaptive embeddings (Zero-shot / LoRA) with Generative Topic Modeling & Agent-based workflow for social science text mining

Douban platform crawler system + visual information management and sentiment analysis platform

An interactive dashboard for exploring mathematical research trends on arXiv

Text Mining Final Project about Twitter Topic Modeling with different models

Topic modeling for NYT articles.

Slides, Notebook and Data for Presentation: DataHour: Harnessing ML and NLP for Elevated Customer Experiences

We present our concept of a new type of Active-Learning for Deep Learning with NLP text classification and experimentally prove its performance against Random Sampling as well as its runtime performance on the Security Threat dataset from CySecAlert. These new Active Learning algorithms are based on Sentence-BERT and BERTopic clustering algorithms with allow us to generate fixed length tokens for whole sentences to make them comparable to each other. Further the Tokens are Clustered using K-Means or HDBScan to get diverse clusters to pick the samples out of them.

Forecasting Private Capital Market using published research and patents. Project developed at Michigan State University under the guidance of Dr. Mohammed Ghassemi for JP Morgan Chase.

AI-powered YouTube comment analysis with BERT sentiment detection, BERTopic clustering, and Ollama AI summaries. Built with Next.js 15, FastAPI, and HuggingFace transformers.

Topic modelling and analysis of different UK newspapers, primarily using BERTopic

Build interactive topic modeling pipelines.

Submission for CL4HEALTH @ LREC-COLING 2024

Meta-Lingo is a comprehensive desktop application designed for corpus linguistics research. Built with modern technologies (Electron + React + Python FastAPI), it provides powerful tools for multimodal corpus management, linguistic analysis, and annotation.

No description provided.

This repository contains a project that utilizes BERTopic for topic modeling on the neuralwork/arxiver dataset of research paper abstracts.

Hierarchical Topic Modeling

Using BERTopic for topic modelling and analyzing Arxiv research paper dataset

This projects contains a nlp pipeline for topic labelling with BERTopic

Kaggle Gold Medal (13th Place) Submission to Google's LLM Prompt Recovery Challenge

Aspect Based Sentiment Analysis (ABSA) of Customer Reviews

A content-based recommendation system for Hacker News using topic modeling (BERTopic)

BERT-based Topic Modeling on New York Times Headlines (160k rows)

Text Mining Orkut’s Community Data with Python: Cultural Memory, Platform Neglect, and Digital Amnesia

NLP Topic Modeling Techniques (LDA, LSA & BERTopic)