Text Summarization using LSTM_Attention, TextRank,PyTextRank, LexRank, Gensim and PyTeaser

Pre-trained word vectors of 30+ languages

bias analysis with NLP on partisan news portals from argentina

Toy project for text data cleaning, pandas DataFrame handling, training bigram models and word2vec models. Also contains search and question answering capabilities based on Haystack.

Анализ корпуса писем времен Великой Отечественной войны с использованием методов машинного обучения. This repository describes my work on the digital humanities research about The Great Patriotic War

Youtube Transcript Summarizer is a Search Engine Extension that works with Youtube to extract the key points of a video and make them accessible to the user.

Investigating the similarity of the texts on the uploaded batch of text files

Die Skripte in diesem Repository sind im Rahmen der Dokumentenanalyse (v. a. Topic Modeling) in Kooperation mit Polit-X entstanden.

Which Novel Do I Belong To? - Deeplearning (LSTM) on top of Keras (Tensorflow)

使用LDA模型提取n个句子的主题，并统计每个主题出现的频次。LDA model is used to extract the topic of N sentences, and the frequency of each topic is counted.

Uses Beautiful Soup to read Wiki pages, Gensim to summarize, NLTK to process, and extracts keywords based on entropy: everything in one beautiful code. A simple but effective solution to extractive text summarization.

An implementation of Topic Modeling with Gensim and NLTK

Unsupervised Topic Modelling project using Latent Dirichlet Allocation (LDA) on the NeurIPS papers. Built as part of the final project for McGill AI Society's Accelerated Introduction to Machine Learning Course (MAIS 202).

Реализация командного проекта для "Газпром нефть"

Topic modelling using gensim

A basic word-embedding model to find best matching students or professors, and recommend the top n results to a specific student

Review of Latent Dirichlet Allocation (LDA) for topic extraction of product reviews for use by product managers. Explores high level overview of LDA, popular libraries, and potential improvements to or over LDA for topic extraction of reviews.

Finding keywords in news headlines that affect market sentiment, usng 2 different datasets from Kaggle, combine them, attached price data and running Tfidf_Elastic_net