メインコンテンツへスキップ

ホーム Python

コース

spaCyで学ぶAdvanced NLP

中級スキルレベル

更新日 2024/11

spaCyで、ルールベースと機械学習の両方を用いた高度な自然言語理解システムの構築方法を学びます。

コースを無料で開始

PythonMachine Learning

5時間

15 ビデオ

55 演習

4,450 XP

21,669

修了証明書

何千もの企業の従業員が支持

チームのトレーニングを担当していますか？

Businessをお試しください

コース説明

大量のテキストを扱うと、いずれ「もっと詳しく知りたい」と思うようになります。たとえば、テキストの内容は何か？文脈の中で単語は何を意味するのか？誰が誰に対して何をしているのか？どの企業や製品が言及されているのか？どのテキスト同士が似ているのか？このコースでは、PythonのNLP向けライブラリとして急速に業界標準となっているspaCyを使い、ルールベースとMachine Learningの両アプローチで高度な自然言語理解システムを構築する方法を学びます。

前提条件

Introduction to Natural Language Processing in Python

1

Finding words, phrases, names and concepts

This chapter will introduce you to the basics of text processing with spaCy. You'll learn about the data structures, how to work with statistical models, and how to use them to predict linguistic features in your text.

Introduction to spaCy

Getting Started

Documents, spans and tokens

Lexical attributes

Statistical models

Model packages

Loading models

Predicting linguistic annotations

Predicting named entities in context

Rule-based matching

Using the Matcher

Writing match patterns

チャプターを開始

2

Large-scale data analysis with spaCy

In this chapter, you'll use your new skills to extract specific information from large volumes of text. You'll learn how to make the most of spaCy's data structures, and how to effectively combine statistical and rule-based approaches for text analysis.

Data Structures (1)

Strings to hashes

Vocab, hashes and lexemes

Data Structures (2)

Creating a Doc

Docs, spans and entities from scratch

Data structures best practices

Word vectors and similarity

Inspecting word vectors

Comparing similarities

Combining models and rules

Debugging patterns (1)

Debugging patterns (2)

Efficient phrase matching

Extracting countries and relationships

チャプターを開始

3

Processing Pipelines

This chapter will show you to everything you need to know about spaCy's processing pipeline. You'll learn what goes on under the hood when you process a text, how to write your own components and add them to the pipeline, and how to use custom attributes to add your own meta data to the documents, spans and tokens.

Processing pipelines

What happens when you call nlp?

Inspecting the pipeline

Custom pipeline components

Use cases for custom components

Simple components

Complex components

Extension attributes

Setting extension attributes (1)

Setting extension attributes (2)

Entities and extensions

Components with extensions

Scaling and performance

Processing streams

Processing data with context

Selective processing

チャプターを開始

4

Training a neural network model

In this chapter, you'll learn how to update spaCy's statistical models to customize them for your use case – for example, to predict a new entity type in online comments. You'll write your own training loop from scratch, and understand the basics of how training works, along with tips and tricks that can make your custom NLP projects more successful.

Training and updating models

Purpose of training

Creating training data (1)

Creating training data (2)

The training loop

Setting up the pipeline

Building a training loop

Exploring the model

Training best practices

Good data vs. bad data

Training multiple labels

Wrapping up

チャプターを開始

spaCyで学ぶAdvanced NLP

コース完了

修了証明書を取得

この修了書をLinkedInや履歴書、CVに追加しましょう
ソーシャルメディアや人事評価で共有しましょう今すぐ登録

19百万人を超える学習者と共にspaCyで学ぶAdvanced NLPを始めましょう！

DataCamp for Mobileでデータスキルを磨きましょう

モバイルコースと毎日の 5 分間のコーディングチャレンジで、外出先でも進歩できます。