Deep contextualized word representations for Chinese

Web服务：使用腾讯 800 万词向量模型和 spotify annoy 引擎得到相似关键词

Problem Statement: Given the tweets from customers about various tech firms who manufacture and sell mobiles, computers, laptops, etc, the task is to identify if the tweets have a negative sentiment towards such companies or products.

A pretrained word2vec embeddings for italian languages

Word embeddings for Italian language, spacy2 prebuilt model

Fake News Detection using related Headline Article pair

Deep Visual-Semantic Embeddings

Document clustering with word vectors.

A collection of PyTorch implementations of GPT-2 to generate stories interactively or autonomously done during my Internship at the University College Dublin in the Computational Creativity Group

Removes foreign and non-language words from Facebook’s fastText vec-file

Identifying Interpretable Word Vector Subspaces with PCA

A package that split misspelled words semantically

Source code for Graded Weighted Bag of Word Model (Coling 2016)

This repo will have all the codes for our Pattern Recognition Lab university course.

How to train Word2Vec for your language.

Categorizing Product reviews in appropriate categories.

Visualization of word embeddings using various algorithms.

Simple & Effective Dimensionality Reduction for Word Embeddings. Presented at NIPS 2017 LLLD & RepL4NLP 2019 Workshop.

Pre-trained word vectors of 30 languages