{"product_id":"110959","title":"Korean embedding ","description":"\u003ccenter\u003e\u003cdiv style=\"text-align:center\"\u003e\u003cimg src=\"https:\/\/tmgdisk01.cafe24.com\/images\/vs\/4172\/sv\/3jYEhpyo3tsKi3gR1IECPfGjstsQfR.png?v=1765045385\" style=\"max-width:100%;max-height:10px\"\u003e\u003c\/div\u003e\u003c\/center\u003e\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\u003ccenter\u003e\n\n\u003cdiv style=\"width:95%\"\u003e\n\n\u003cdiv style=\"text-align:center;font-size:30px;font-weight:bolder;line-height:1.6em\"\u003e Korean embedding \u003c\/div\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003cdiv style=\"border-bottom:1px;border-bottom-style:dotted;border-color:;padding-bottom:20px\"\u003e\u003ccenter\u003e\u003ctable align=\"center\" width=\"100%\"\u003e\u003ctbody style=\"border:0px\"\u003e\n\n\u003ctr\u003e\u003ctd align=\"center\" style=\"line-height:1.2em;text-align:center;font-size:18px;color:black;font-weight:bold;padding-bottom:20px;\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\n\n\u003ctr\u003e\u003ctd style=\"text-align:center\"\u003e\u003cimg src=\"https:\/\/image.yes24.com\/goods\/78569687\/XL\" style=\"max-width:100%;height:auto\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\n\n\n\u003c\/tbody\u003e\u003c\/table\u003e\u003c\/center\u003e\u003c\/div\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003cdiv style=\"width:95%;{split_style6}padding-top:20px;padding-bottom:20px\"\u003e\n\n\u003cdiv style=\"text-align:left;font-size:16px;font-weight:bold;padding-bottom:20px\"\u003e Description \u003c\/div\u003e\n\n\u003cdiv style=\"text-align:left;word-break:break-all;font-size:14px;line-height:1.6em;\"\u003e\n\n\u003cdiv\u003e\u003ch5\u003e \u003cb\u003eBook Introduction\u003c\/b\u003e\n\u003c\/h5\u003e\u003c\/div\u003e\n\u003cdiv\u003e\n\u003cdiv\u003e\u003cdiv\u003e \u003cb\u003eThe Key to Improving the Performance of Natural Language Processing Models: Korean Embedding\u003c\/b\u003e\u003cbr\u003e \u003cbr\u003eEmbedding is a term that refers to the result of converting natural language into a vector, which is a list of numbers, or the entire process of doing so.\u003cbr\u003e The name embedding comes from the idea of ​​converting each word or sentence into a vector and 'embedding' it into a vector space.\u003cbr\u003e To enable computers to process natural language, natural language must be converted into a computable form called an embedding.\u003cbr\u003e\u003cbr\u003e\u003cbr\u003e Embeddings play a very important role as the first gateway for computers to understand natural language.\u003cbr\u003e It is no exaggeration to say that the performance of a natural language processing model is determined by embedding.\u003cbr\u003e This book provides a comprehensive overview of various embedding techniques and introduces the entire process, from Korean data preprocessing to embedding construction, in a tutorial format.\u003cbr\u003e It covers everything from word-level techniques such as Word2Vec to sentence-level embeddings such as ELMo and BERT.\u003cbr\u003e\n\n\u003c\/div\u003e\u003c\/div\u003e\n\u003cdiv\u003e\u003cul\u003e\u003cli\u003e You can preview some of the book's contents.\u003cbr\u003e \u003cspan\u003ePreview\u003c\/span\u003e\n\n\u003c\/li\u003e\u003c\/ul\u003e\u003c\/div\u003e\n\u003c\/div\u003e\n\u003cbr\u003e\u003cdiv\u003e\u003ch5\u003e \u003cb\u003eindex\u003c\/b\u003e\n\u003c\/h5\u003e\u003c\/div\u003e\n\u003cdiv\u003e\n\u003cdiv\u003e \u003cb\u003eChapter 1.\u003c\/b\u003e \u003cbr\u003eintroduction\u003cbr\u003e 1.1 What is embedding?\u003cbr\u003e 1.2 The Role of Embedding\u003cbr\u003e 1.2.1 Calculating word\/sentence relevance\u003cbr\u003e 1.2.2 Implication of semantic\/grammatical information\u003cbr\u003e 1.2.3 Transfer Learning\u003cbr\u003e 1.3 History and types of embedding techniques\u003cbr\u003e 1.3.1 From statistical to neural network based\u003cbr\u003e 1.3.2 From word level to sentence level\u003cbr\u003e 1.3.3 Rule → End-to-end → Pretrain\/Fine Tuning\u003cbr\u003e 1.3.4 Types and Performance of Embeddings\u003cbr\u003e 1.4 Development Environment\u003cbr\u003e 1.4.1 Introduction to the Environment\u003cbr\u003e 1.4.2 AWS Configuration\u003cbr\u003e 1.4.3 Code Execution\u003cbr\u003e 1.4.4 Bug Reports and Q\u0026amp;A\u003cbr\u003e 1.4.5 Open sources that this book is using\u003cbr\u003e 1.5 Data and Key Terms Covered in This Book\u003cbr\u003e 1.6 Summary of this chapter\u003cbr\u003e 1.7 References\u003cbr\u003e\u003cbr\u003e \u003cb\u003eChapter 2.\u003cbr\u003e How Vectors Gain Meaning\u003c\/b\u003e\u003cbr\u003e 2.1 Natural language computation and understanding\u003cbr\u003e 2.2 Which words are used the most?\u003cbr\u003e 2.2.1 Back of Wars Assumptions\u003cbr\u003e 2.2.2 TF-IDF\u003cbr\u003e 2.2.3 Deep Averaging Network\u003cbr\u003e 2.3 In what order are the words written?\u003cbr\u003e 2.3.1 Statistical-based language models\u003cbr\u003e 2.3.2 Neural Network-Based Language Model\u003cbr\u003e 2.4 Which words are used together?\u003cbr\u003e 2.4.1 Distribution Assumptions \u003cbr\u003e2.4.2 Distribution and Meaning (1): Morphemes\u003cbr\u003e 2.4.3 Distribution and Meaning (2): Parts of Speech\u003cbr\u003e 2.4.4 Point-wise mutual information\u003cbr\u003e 2.4.5 Word2Vec\u003cbr\u003e 2.5 Summary of this chapter\u003cbr\u003e 2.6 References\u003cbr\u003e\u003cbr\u003e \u003cb\u003eChapter 3.\u003cbr\u003e Korean preprocessing\u003c\/b\u003e\u003cbr\u003e 3.1 Data Acquisition\u003cbr\u003e 3.1.1 Korean Wikipedia\u003cbr\u003e 3.1.2 KorQuAD\u003cbr\u003e 3.1.3 Naver Movie Review Corpus\u003cbr\u003e 3.1.4 Downloading preprocessed data\u003cbr\u003e 3.2 Morphological analysis based on supervised learning\u003cbr\u003e 3.2.1 How to use KoNLPy\u003cbr\u003e 3.2.2 Analysis of performance differences by analyzer within KoNLPy\u003cbr\u003e 3.2.3 How to use Khaiii\u003cbr\u003e 3.2.4 Adding a User Dictionary to Eunjeonhannyeon\u003cbr\u003e 3.3 Morphological analysis based on unsupervised learning\u003cbr\u003e 3.3.1 soynlp morphological analyzer\u003cbr\u003e 3.3.2 Google Sentence Piece\u003cbr\u003e 3.3.3 Spacing Correction\u003cbr\u003e 3.3.4 Downloading completed morphological analysis data\u003cbr\u003e 3.4 Summary of this chapter\u003cbr\u003e 3.5 References\u003cbr\u003e\u003cbr\u003e \u003cb\u003eChapter 4.\u003cbr\u003e Word-level embeddings\u003c\/b\u003e\u003cbr\u003e 4.1 NPLM\u003cbr\u003e 4.1.1 Model Basic Structure\u003cbr\u003e 4.1.2 Learning of NPLM\u003cbr\u003e 4.1.3 NPLM and Semantic Information\u003cbr\u003e 4.2 Word2Vec\u003cbr\u003e 4.2.1 Model Basic Structure\u003cbr\u003e 4.2.2 Building training data\u003cbr\u003e 4.2.3 Model Training\u003cbr\u003e 4.2.4 Tutorial\u003cbr\u003e 4.3 FastText\u003cbr\u003e 4.3.1 Model Basic Structure\u003cbr\u003e 4.3.2 Tutorial \u003cbr\u003e4.3.3 Korean Characters and FastText\u003cbr\u003e 4.4 Latent Semantic Analysis\u003cbr\u003e 4.4.1 PPMI matrix\u003cbr\u003e 4.4.2 Understanding Latent Semantics through Matrix Decomposition\u003cbr\u003e 4.4.3 Understanding Word2Vec through Matrix Decomposition\u003cbr\u003e 4.4.4 Tutorial\u003cbr\u003e 4.5 GloVe\u003cbr\u003e 4.5.1 Model Basic Structure\u003cbr\u003e 4.5.2 Tutorial\u003cbr\u003e 4.6 Swivel\u003cbr\u003e 4.6.1 Model Basic Structure\u003cbr\u003e 4.6.2 Tutorial\u003cbr\u003e 4.7 Which word embeddings to use\u003cbr\u003e 4.7.1 Downloading word embeddings\u003cbr\u003e 4.7.2 Word similarity evaluation\u003cbr\u003e 4.7.3 Word analogy evaluation\u003cbr\u003e 4.7.4 Visualizing Word Embeddings\u003cbr\u003e 4.8 Weighted Embedding\u003cbr\u003e 4.8.1 Model Overview\u003cbr\u003e 4.8.2 Model Implementation\u003cbr\u003e 4.8.3 Tutorial\u003cbr\u003e 4.9 Summary of this chapter\u003cbr\u003e 4.10 References\u003cbr\u003e\u003cbr\u003e \u003cb\u003eChapter 5.\u003cbr\u003e sentence-level embeddings\u003c\/b\u003e\u003cbr\u003e 5.1 Latent Semantic Analysis\u003cbr\u003e 5.2 Doc2Vec\u003cbr\u003e 5.2.1 Model Overview\u003cbr\u003e 5.2.2 Tutorial\u003cbr\u003e 5.3 Latent Dirichlet Allocation\u003cbr\u003e 5.3.1 Model Overview\u003cbr\u003e 5.3.2 Architecture\u003cbr\u003e 5.3.3 LDA and Gibbs Sampling\u003cbr\u003e 5.3.4 Tutorial\u003cbr\u003e 5.4 ELMo\u003cbr\u003e 5.4.1 Character-level convolutional layer\u003cbr\u003e 5.4.2 Bidirectional LSTM, Score Layer\u003cbr\u003e 5.4.3 ELMo Layer\u003cbr\u003e 5.4.4 Free Train Tutorial\u003cbr\u003e 5.5 Transformer Network\u003cbr\u003e 5.5.1 Scaled Dot-Product Attention \u003cbr\u003e5.5.2 Multihead Attention\u003cbr\u003e 5.5.3 Position-wise Feed-Forward Networks\u003cbr\u003e 5.5.4 Transformer Learning Strategies\u003cbr\u003e 5.6 BERT\u003cbr\u003e 5.6.1 BERT, ELMo, GPT\u003cbr\u003e 5.6.2 Pretraining Tasks and Building Training Data\u003cbr\u003e 5.6.3 BERT Model Structure\u003cbr\u003e 5.6.4 Free Train Tutorial\u003cbr\u003e 5.7 Summary of this chapter\u003cbr\u003e 5.8 References\u003cbr\u003e\u003cbr\u003e \u003cb\u003eChapter 6.\u003cbr\u003e Embedding Fine Tuning\u003c\/b\u003e\u003cbr\u003e 6.1 Pretrain and Fine Tuning\u003cbr\u003e 6.2 Creating a Pipeline for Classification\u003cbr\u003e 6.3 Using word embeddings\u003cbr\u003e 6.3.1 Network Overview\u003cbr\u003e 6.3.2 Network Implementation\u003cbr\u003e 6.3.3 Tutorial\u003cbr\u003e 6.4 Using ELMo\u003cbr\u003e 6.4.1 Network Overview\u003cbr\u003e 6.4.2 Network Implementation\u003cbr\u003e 6.4.3 Tutorial\u003cbr\u003e 6.5 Using BERT\u003cbr\u003e 6.5.1 Network Overview\u003cbr\u003e 6.5.2 Network Implementation\u003cbr\u003e 6.5.3 Tutorial\u003cbr\u003e 6.6 Which sentence embeddings to use\u003cbr\u003e 6.7 Summary of this chapter\u003cbr\u003e 6.8 References\u003cbr\u003e\u003cbr\u003e \u003cb\u003esupplement\u003c\/b\u003e\u003cbr\u003e Appendix A.\u003cbr\u003e Fundamentals of Linear Algebra\u003cbr\u003e 1.1 Vector and matrix operations\u003cbr\u003e 1.2 Inner product and covariance\u003cbr\u003e 1.3 Dot product and projection\u003cbr\u003e 1.4 Inner products and linear transformations\u003cbr\u003e 1.5 Matrix factorization-based dimensionality reduction (1): Principal component analysis (PCA) \u003cbr\u003e1.6 Matrix factorization-based dimensionality reduction (2): Singular value decomposition (SVD)\u003cbr\u003e\u003cbr\u003e \u003cb\u003eAppendix B.\u003cbr\u003e Probability Theory Fundamentals\u003c\/b\u003e\u003cbr\u003e 2.1 Random variables and probability distributions\u003cbr\u003e 2.2 Bayesian probability theory\u003cbr\u003e\u003cbr\u003e \u003cb\u003eAppendix C.\u003cbr\u003e Neural Network Basics\u003c\/b\u003e\u003cbr\u003e 3.1 Understanding Neural Networks with DAG\u003cbr\u003e 3.2 Neural networks are probabilistic models.\u003cbr\u003e 3.3 Maximum likelihood estimation and learning loss\u003cbr\u003e 3.4 Gradient descent\u003cbr\u003e 3.5 Backpropagation by computational node\u003cbr\u003e 3.6 CNN and RNN\u003cbr\u003e\u003cbr\u003e \u003cb\u003eAppendix D.\u003cbr\u003e Basic Korean Language\u003c\/b\u003e\u003cbr\u003e 4.1 Syntactic units\u003cbr\u003e 4.2 Sentence Types\u003cbr\u003e 4.3 Parts of speech\u003cbr\u003e 4.4 Amount and tense\u003cbr\u003e 4.5 Topic\u003cbr\u003e 4.6 Increase\u003cbr\u003e 4.7 Aspect\u003cbr\u003e 4.8 Semantic role\u003cbr\u003e 4.9 Passive\u003cbr\u003e 4.10 Sadong\u003cbr\u003e 4.11 Denial\u003cbr\u003e\u003cbr\u003e \u003cb\u003eAppendix E.\u003cbr\u003e References\u003c\/b\u003e\n\u003c\/div\u003e\n\u003cdiv\u003e\u003c\/div\u003e\n\u003c\/div\u003e\n\u003cbr\u003e\u003cdiv\u003e\u003ch5\u003e \u003cb\u003eDetailed image\u003c\/b\u003e \u003c\/h5\u003e\u003c\/div\u003e\n\u003cdiv\u003e\u003cdiv\u003e\u003cimg src=\"https:\/\/image.yes24.com\/momo\/TopCate2557\/MidCate008\/255676070(1).jpg\" border=\"0\" alt=\"Detailed Image 1\"\u003e\u003c\/div\u003e\u003c\/div\u003e\n\u003cbr\u003e\u003cdiv\u003e\u003ch5\u003e \u003cb\u003ePublisher's Review\u003c\/b\u003e\n\u003c\/h5\u003e\u003c\/div\u003e\n\u003cdiv\u003e\n\u003cdiv\u003e \u003cb\u003eWhat this book covers\u003c\/b\u003e\u003cbr\u003e\u003cbr\u003e ■ Introduction to the concept, types, and history of embedding, the first gateway to natural language processing.\u003cbr\u003e ■ Theoretical background explaining how embeddings encapsulate natural language meaning\u003cbr\u003e ■ Sharing know-how on preprocessing Korean corpora, including Wikipedia and KorQuAD\u003cbr\u003e ■ KoNLPy, soynlp, and Google Sentencepiece Package Guide \u003cbr\u003e■ Word-level embeddings such as Word2Vec, GloVe, FastText, and Swivel\u003cbr\u003e ■ Description of sentence-level embeddings such as LDA, Doc2Vec, ELMo, and BERT\u003cbr\u003e ■ The tutorial will begin after explaining the individual model learning and operation process at the code level.\u003cbr\u003e ■ Embedding fine-tuning practice focusing on document classification tasks\u003cbr\u003e\u003cbr\u003e This book introduces various embedding techniques.\u003cbr\u003e We will broadly cover word-level embeddings and sentence-level embeddings.\u003cbr\u003e It is a technique for converting each word and sentence into a vector.\u003cbr\u003e Word-level embeddings described here include Word2Vec, GloVe, FastText, and Swivel.\u003cbr\u003e Sentence-level embeddings include ELMo and BERT.\u003cbr\u003e This book examines the theoretical background of each embedding technique and then explains the process of building actual embeddings using a Korean corpus.\u003cbr\u003e When explaining each technique, try to follow the formulas and notations of the original paper as much as possible.\u003cbr\u003e The code will also be introduced from the official repository of the paper's authors.\u003cbr\u003e \u003cbr\u003eCorpus preprocessing and embedding fine-tuning are also important topics covered in this book.\u003cbr\u003e The former is a process that must be done before building the embedding, and the latter is a process that must be done after building the embedding.\u003cbr\u003e For preprocessing, we explain how to use open source tools such as KoNLPy, soynlp, and Google Sentencepiece.\u003cbr\u003e We will practice fine-tuning embeddings using the example of a document classification task that predicts the polarity of a document, such as positive or negative.\u003cbr\u003e\u003cbr\u003e The main contents of each chapter are as follows.\u003cbr\u003e\u003cbr\u003e Chapter 1, 'Introduction', examines the definition, history, and types of embedding.\u003cbr\u003e The process of setting up a development environment such as Docker is also explained.\u003cbr\u003e\u003cbr\u003e Chapter 2, \"How Vectors Gain Meaning,\" introduces how to embed the meaning of natural language into embeddings. \u003cbr\u003eAlthough each embedding technique has its own differences, it is important to note that they share a common characteristic: they reflect statistical pattern information in the corpus.\u003cbr\u003e\u003cbr\u003e Chapter 3, 'Korean Preprocessing', covers the preprocessing process of Korean data for embedding learning.\u003cbr\u003e This explains how to convert data in the form of web documents or JSON files into pure text files and perform morphological analysis on them.\u003cbr\u003e Spacing correction is also introduced.\u003cbr\u003e\u003cbr\u003e Chapter 4, \"Word-Level Embedding,\" describes various word-level embedding models. NPLM, Word2Vec, and FastText are prediction-based models, while LSA, GloVe, and Swivel are matrix factorization-based techniques.\u003cbr\u003e Weighted embedding is a method that extends word embedding to the sentence level.\u003cbr\u003e\u003cbr\u003e Chapter 5, 'Sentence-Level Embeddings', covers sentence-level embeddings. \u003cbr\u003eWe introduce three types: matrix factorization, probabilistic models, and neural network-based models.\u003cbr\u003e Latent semantic analysis (LSA) is a matrix factorization, latent Dirichlet allocation (LDA) is a probabilistic model, and Doc2Vec, ELMo, and BERT are methods that focus on neural networks.\u003cbr\u003e In particular, BERT is based on a self-attention-based transformer network.\u003cbr\u003e\u003cbr\u003e Chapter 6, \"Fine-Tuning Embeddings,\" covers fine-tuning word- and sentence-level embeddings.\u003cbr\u003e We perform a task of classifying polarity using a corpus of Naver movie reviews.\u003cbr\u003e\u003cbr\u003e The 'Appendix' briefly reviews the basic knowledge needed to understand this book.\u003cbr\u003e Explains key concepts such as linear algebra, probability theory, neural networks, and Korean linguistics. \u003cbr\u003e\n\n\u003c\/div\u003e\n\u003cdiv\u003e\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\n\n\u003c\/div\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003cdiv style=\"width:95%;padding-top:20px;padding-bottom:20px\"\u003e\n\n\u003cdiv style=\"text-align:left;font-size:16px;font-weight:bold;padding-bottom:20px\"\u003e GOODS SPECIFICS \u003c\/div\u003e\n\n\u003cdiv style=\"text-align:left;font-size:14px;line-height:1.6em;\"\u003e\n\n\u003cdiv style=\"width:100%;margin-bottom:5px;line-height:1.6em;font-size:14px\"\u003e - \u003cstrong\u003eDate of publication:\u003c\/strong\u003e September 26, 2019\u003c\/div\u003e\n\n\u003cdiv style=\"width:100%;margin-bottom:5px;line-height:1.6em;font-size:14px\"\u003e - \u003cstrong\u003ePage count, weight, size:\u003c\/strong\u003e 348 pages | 188*235*30mm\u003c\/div\u003e\n\n\u003cdiv style=\"width:100%;margin-bottom:5px;line-height:1.6em;font-size:14px\"\u003e - \u003cstrong\u003eISBN13:\u003c\/strong\u003e 9791161753508\u003c\/div\u003e\n\n \u003cdiv style=\"width:100%;margin-bottom:5px;line-height:1.6em;font-size:14px\"\u003e- \u003cstrong\u003eISBN10:\u003c\/strong\u003e 1161753508 \u003c\/div\u003e\n\n\n\u003c\/div\u003e\n\n\n\u003c\/div\u003e\n\n\n\u003c\/div\u003e\n\n\u003ccenter\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003ccenter\u003e\u003ctable\u003e\u003ctr\u003e\u003ctd style=\"height:10px\"\u003e\u003c\/td\u003e\u003c\/tr\u003e\u003c\/table\u003e\u003c\/center\u003e\n\n\u003cspan\u003e\u003c\/span\u003e\n\n\u003c\/center\u003e\n\n\n\u003c\/center\u003e","brand":"LIBRAIRIE COREENNE","offers":[{"title":"Default Title","offer_id":43892916289578,"sku":"110959","price":44.0,"currency_code":"EUR","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0683\/2750\/5962\/files\/c8895f08128ff9066fb11e20b8c07cd1.jpg?v=1765382461","url":"https:\/\/librairie.coreenne.fr\/en\/products\/110959","provider":"LIBRAIRIE COREENNE","version":"1.0","type":"link"}