Sentiment Analysis with Deep Learning using BERT

4.5
281 個評分
提供方
Coursera Project Network
9,119 人已註冊
在此指導項目中,您將:

Preprocess and clean data for BERT Classification

Load in pretrained BERT with custom output layer

Train and evaluate finetuned BERT architecture on your own problem statement

Clock120 minutes
Intermediate中級
Cloud無需下載
Video分屏視頻
Comment Dots英語(English)
Laptop僅限桌面

In this 2-hour long project, you will learn how to analyze a dataset for sentiment analysis. You will learn how to read in a PyTorch BERT model, and adjust the architecture for multi-class classification. You will learn how to adjust an optimizer and scheduler for ideal training and performance. In fine-tuning this model, you will learn how to design a train and evaluate loop to monitor model performance as it trains, including saving and loading models. Finally, you will build a Sentiment Analysis model that leverages BERT's large-scale language knowledge. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.

您要培養的技能

Natural Language ProcessingDeep LearningMachine LearningSentiment AnalysisBERT

分步進行學習

在與您的工作區一起在分屏中播放的視頻中,您的授課教師將指導您完成每個步驟:

  1. Introduction to BERT and the problem at hand

  2. Exploratory Data Analysis and Preprocessing

  3. Training/Validation Split

  4. Loading Tokenizer and Encoding our Data

  5. Setting up BERT Pretrained Model

  6. Creating Data Loaders

  7. Setting Up Optimizer and Scheduler

  8. Defining our Performance Metrics

  9. Creating our Training Loop

  10. Loading and Evaluating our Model

指導項目工作原理

您的工作空間就是瀏覽器中的雲桌面,無需下載

在分屏視頻中,您的授課教師會為您提供分步指導

講師

審閱

來自SENTIMENT ANALYSIS WITH DEEP LEARNING USING BERT的熱門評論

查看所有評論

常見問題

常見問題

還有其他問題嗎?請訪問 學生幫助中心