2 月 12 日 专知

【导读】推荐一本PyTorch进行自然语言处理实战的书:《Natural Language Processing with PyTorch》,手把手教你PyTorch基础,以及NLP上如何一步步应用,书中提供详细代码示例,感兴趣的同学下载学习。



作者Delip RaoBrianMcMahon在NLP和深度学习算法方面为您提供了坚实的基础,并演示了如何使用PyTorch构建应用程序,其中包含针对您所面临的问题的丰富文本表示。每一章包括几个代码示例和插图。

  • 探索计算图和监督学习范例

  • 掌握PyTorch优化张量操作库的基础知识

  • 概述传统的NLP概念和方法

  • 了解构建神经网络所涉及的基本思想

  • 使用嵌入来表示单词,句子,文档和其他特征

  • 探索序列预测并生成序列到序列模型

  • 学习构建生产NLP系统的设计模式

【PoTorch NLP实战代码下载】


  • 后台回复“PytorchNLP” 就可以获取《代码》的下载链接~ 



Natural Language Processing with PyTorch

Build Intelligent Language Applications Using Deep Learning 
By Delip Rao and Brian McMahan

Welcome. This is a companion repository for the book Natural Language Processing with PyTorch: Build Intelligent Language Applications Using Deep Learning.

Table of Contents

  • Get Started!

  • Chapter 1: Introduction

    • PyTorch Basics

  • Chapter 2: A Quick Tour of NLP

  • Chapter 3: Foundational Components of Neural Networks

    • In-text examples

    • Diving deep into supervised training

    • Classifying sentiment of restaurant reviews using a Perceptron

  • Chapter 4: Feed-forward Networks for NLP

    • Limitations of the Perceptron

    • Introducing Multi-layer Perceptrons (MLPs)

    • Introducing Convolutional Neural Networks (CNNs)

    • Surname Classification with an MLP

    • Surname Classification with a CNN

  • Chapter 5: Embedding Words and Types

    • Using Pretrained Embeddings

    • Learning Continous Bag-of-words Embeddings (CBOW)

    • Transfer Learning using Pre-trained Embeddings

  • Chapter 6: Sequence Modeling for NLP

    • A sequence representation for Surnames

  • Chapter 7: Intermediate Sequence Modeling for NLP

    • Generating novel surnames from sequence representations

    • Uncondition generation

    • Conditioned generation

  • Chapter 8: Advanced Sequence Modeling for NLP

    • Understanding PackedSequences

    • Sequence to Sequence Learning

    • Attention

    • Neural Machine Translation

  • Chapter 9: Classics, Frontiers, Next Steps


专 · 知






点赞 0

Recommender systems are widely used in big information-based companies such as Google, Twitter, LinkedIn, and Netflix. A recommender system deals with the problem of information overload by filtering important information fragments according to users' preferences. In light of the increasing success of deep learning, recent studies have proved the benefits of using deep learning in various recommendation tasks. However, most proposed techniques only aim to target individuals, which cannot be efficiently applied in group recommendation. In this paper, we propose a deep learning architecture to solve the group recommendation problem. On the one hand, as different individual preferences in a group necessitate preference trade-offs in making group recommendations, it is essential that the recommendation model can discover substitutes among user behaviors. On the other hand, it has been observed that a user as an individual and as a group member behaves differently. To tackle such problems, we propose using an attention mechanism to capture the impact of each user in a group. Specifically, our model automatically learns the influence weight of each user in a group and recommends items to the group based on its members' weighted preferences. We conduct extensive experiments on four datasets. Our model significantly outperforms baseline methods and shows promising results in applying deep learning to the group recommendation problem.

点赞 0