Applied Natural Language Processing in the Enterprise: Teaching Machines to Read, Write, and Understand

NLP has exploded in popularity over the last few years. But while Google, Facebook, OpenAI, and others continue to release larger language models, many teams still struggle with building NLP applications that live up to the hype. This hands-on guide helps you get up to speed on the latest and most promising trends in NLP.

With a basic understanding of machine learning and some Python experience, you'll learn how to train and deploy real-world NLP applications in your organization. Authors Ankur Patel and Ajay Uppili Arasanipalai guide you through the process using code and examples that highlight the best practices in modern NLP.

• Use state-of-the-art NLP models such as BERT and GPT-3 to solve NLP tasks such as named entity recognition, text classification, semantic search, and reading comprehension
• Train NLP models with performance comparable or superior to that of out-of-the-box systems
• Learn about transformer architecture and modern tricks like transfer learning that have taken the NLP world by storm
• Become familiar with the tools of the trade, including spaCy, Hugging Face, and fast.ai
• Use Python and PyTorch to build core parts of the NLP pipeline from scratch, including tokenizers, embeddings, and language models
• Take your models out of Jupyter notebooks and learn how to deploy, monitor, and maintain them in production

近年來，自然語言處理（NLP）在人氣上蓬勃發展。然而，儘管Google、Facebook、OpenAI等公司不斷推出更大型的語言模型，許多團隊仍然在建立符合炒作期望的NLP應用上遇到困難。這本實用指南將幫助您了解NLP領域最新且最有前景的趨勢。

在具備基本的機器學習知識和一些Python經驗的基礎上，您將學習如何在組織中訓練和部署真實世界的NLP應用。作者Ankur Patel和Ajay Uppili Arasanipalai將通過代碼和示例引導您完成這一過程，並突出現代NLP中的最佳實踐。

本書將教您以下內容：
- 使用BERT和GPT-3等最先進的NLP模型解決NLP任務，如命名實體識別、文本分類、語義搜索和閱讀理解
- 訓練NLP模型，其性能可與開箱即用系統相媲美或優於其性能
- 了解Transformer架構和像是遷移學習等現代技巧，這些技巧已經在NLP領域引起轟動
- 熟悉相關工具，包括spaCy、Hugging Face和fast.ai
- 使用Python和PyTorch從頭開始構建NLP流程的核心部分，包括分詞器、嵌入和語言模型
- 將模型從Jupyter筆記本中提取出來，並學習如何在生產環境中部署、監控和維護它們。

Ankur A. Patel is the Co-Founder and Head of Data at Glean and the Co-Founder of Mellow. Glean uses NLP to extract data from invoices and generate vendor spend intelligence for clients. Mellow is on a mission to democratize NLP tasks such as entity resolution, named entity recognition, and text classification for everyone. Previously, Ankur led teams at 7Park Data, ThetaRay, and R-Squared Macro and began his career at Bridgewater Associates and J.P. Morgan. He is a graduate of Princeton University and lives in New York City.

Ajay Arasanipalai is a deep learning researcher and student at University of Illinois at Urbana-Champaign. He's authored many popular articles that discuss state-of-the-art deep learning research. In March 2018, Ajay was invited to speak about accelerated deep learning at Think 2018, IBM's largest annual tech conference. Currently, as cochair of the ACM SIGAI chapter at the University of Illinois, he organizes educational workshops and projects for undergraduate students.

Ankur A. Patel 是 Glean 的聯合創始人兼數據主管，也是 Mellow 的聯合創始人。Glean 使用自然語言處理 (NLP) 從發票中提取數據，為客戶生成供應商支出情報。Mellow 的使命是使每個人都能參與 NLP 任務，如實體解析、命名實體識別和文本分類。之前，Ankur 在 7Park Data、ThetaRay 和 R-Squared Macro 領導團隊，並在 Bridgewater Associates 和 J.P. Morgan 開始了他的職業生涯。他畢業於普林斯頓大學，目前居住在紐約市。

Ajay Arasanipalai 是伊利諾伊大學香檳分校的深度學習研究員和學生。他撰寫了許多熱門文章，討論最先進的深度學習研究。2018年3月，Ajay 被邀請在 Think 2018 上演講，這是 IBM 最大的年度技術會議。目前，作為伊利諾伊大學 ACM SIGAI 分會的聯合主席，他組織了專為本科生舉辦的教育研討會和項目。