Coursera 笔记

Module 04 · Transformer Network

Transformer Network Application: Question AnsweringTransformer 网络应用:问答

Transformer Network Application: Question Answering Transformer 网络应用:问答

Instructions 说明

IMPORTANT 重要

Hey learner,  嗨,学习者

In this ungraded lab, on the top right you'll see a button, "Save and close". Please press it every time when you are no longer running or closing the lab. This helps to release the GPU resources used by your version of the lab, so that other learners can benefit from it as much as you did.
在这个未评分的实验中,右上角你会看到一个按钮,“保存并关闭”。每次当你不再运行或关闭实验时,请按下它。这有助于释放实验版本使用的 GPU 资源,以便其他学习者也能像你一样从中受益。

Thank you and happy learning!
感谢并祝学习愉快!


In this ungraded lab you will perform extractive Question Answering by fine-tuning a pre-trained transformer model to a custom dataset. You will implement a QA model both in TensorFlow and PyTorch.
在这个未评分的实验中,您将通过微调预训练的 Transformer 模型到自定义数据集来执行抽取式问答。您将使用 TensorFlow 和 PyTorch 实现问答模型。

📎 QA_dataset-446a5cf9-4ddb-4df5-aa81-9e0be3cbf2eb.ipynb

Source: https://www.coursera.org/learn/nlp-sequence-models/ungradedLab/6iTj6/transformer-network-application-question-answering