KimMilim

Json parse - practice

I'm going to practice on parsing(Json format) Git commit message based on Python. I'm going to read the data from .csv file and get url. And I will save the message that I parsed from url to .csv file.

I need to import Json, csv

KimMilim

Json parse - practice

I'm going to practice on parsing(Json format) based on Python. I'm going to read the data from .csv file and get url.

need to import Json, csv

import csv

KimMilim

BERT(Bidirectional Encoder Representations from Transformers)_Theory

Paper Link: [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding][https://arxiv.org/abs/1810.04805]

1.Introduce

KimMilim

NN(Neural Network)

NN으로는 자연어처리 불가 여기 더 채우기

RNN(Recurrent Neural Network)

When we use RNN

• handling sequence data (Sentence, Genome, voice signal, sensor sensing data etc..) In the case of a sentence, the meaning of the current word is interpreted not through the current word alone,

KimMilim

Word2Vec_ practice

I'm going to practice on Word2Vec using gensim.

gensim

Gensim is an open-source library for unsupervised topic modeling and natural language processing, using modern statistical machine learning.

KimMilim

Word2Vec_theory ( word2vec works )

Word Embedding

#What is Word Embedding I say Word2Vec Word Embedding converts natural language into a vector that computers can understand. It can make 'looks like' a computer understands natural language. It can measure similarity of between words. It makes it easier to handle by vectoring words. It can make inferences through vector operations. Because the meaning of word itself is digitized as a vector.