Table of Contents
Practical Natural Language Processing Index
Return to Practical Natural Language Processing, Python NLP, NLP, NLP bibliography, Python AI - AI bibliography, Python DL - Machine Learning (ML) bibliography, Python ML - Deep Learning (DL) bibliography, Python Data science - Data Science bibliography
A
- with Prodigy, Case Study: Corporate Ticketing
- Adamic, Lada, Identifying Memes
- adult content filtering, Applications
- AI (see artificial intelligence)
- Allen AI, Peeking over the Horizon
- Grover, Fake News
- Amazon Comprehend Medical, Medical Information Extraction and Analysis-Medical Information Extraction and Analysis
- ambiguity , Ambiguity-Ambiguity
- APIs
- integration of, Rasa NLU
- Apple Siri, NLP: A Primer, NLP in the Real World, NLP Tasks, An NLP Walkthrough: Conversational Agents
- ARC (see Abstraction and Reasoning Corpus)
- Arria, NLP in the Real World
- artificial intelligence (AI), Machine Learning, Deep Learning, and NLP: An Overview, Chatbots, The End-to-End NLP Process
- perspectives on, Peeking over the Horizon
- aspect-based sentiment analysis, Applications-Applications, Aspect-Level Sentiment Analysis-Unsupervised approach
- attention, Outcome prediction and best practices
- attention networks, Troubleshooting and Interpretability
- derived, Attribute Extraction
- auditing, Accounting and auditing
- authorship attribution, Applications
- automation, full, Other Aspects
- AWS (see Amazon Web Services)
B
- Bayes’ theorem, Naive Bayes
- BBC, Template Filling
- BCG, Peeking over the Horizon
- Bender, Emily, Context
- BERT (Bidirectional Encoder Representations from Transformers), Transformers, Universal Text Representations, Models
- text classification with, Text Classification with Large, Pre-Trained Language Models-Text Classification with Large, Pre-Trained Language Models
- BERT for Biomedical Text (BioBERT), Medical Information Extraction and Analysis, Medical Information Extraction and Analysis
- bigram flipping, Data Acquisition
- billing, Patient Prioritization and Billing
- BioBERT (BERT for Biomedical Text), Medical Information Extraction and Analysis, Medical Information Extraction and Analysis
- Bloomberg Terminal, Event Extraction
C
- terminology, Dialog Systems in Detail
- Chee, Cedric, An Example Scenario
- Chollet, François, Peeking over the Horizon
- (see also text classification)
- multiclass, Text Classification
- clpsych.org, Applications
- CNNs (convolutional neural networks), Convolutional neural networks, Deep Learning for Text Classification, CNNs for Text Classification-CNNs for Text Classification, Models
- congratsbot, Event Extraction
- content discovery
- chatbots in, Applications
- convolutional neural networks (CNNs), Deep Learning for Text Classification, CNNs for Text Classification-CNNs for Text Classification, Models
- chatbots in, Applications
- on social channels, Applications, Applications, Customer Support on Social Channels-Memes and Fake News
D
- DARPA, Chatbots
- data annotation, Rasa NLU-Rasa NLU
- (see also pre-processing)
- data science (DS), The End-to-End NLP Process, The Data Science Process-Microsoft Team Data Science Process
- text classification with, One Pipeline, Many Classifiers-One Pipeline, Many Classifiers, Case Study: Corporate Ticketing
- limitations, Why Deep Learning Is Not Yet the Silver Bullet for NLP-Why Deep Learning Is Not Yet the Silver Bullet for NLP
- overview, Machine Learning, Deep Learning, and NLP: An Overview-Machine Learning, Deep Learning, and NLP: An Overview
- with EHRs, Outcome prediction and best practices
- Deloitte, Accounting and auditing
- Demoji, Handling emojis
- dialog act classification, Dialog Act Classification
- dialog act or intent, Dialog Systems in Detail
- dialog systems
- deep reinforcement learning for, Deep Reinforcement Learning for Dialogue Generation-Human-in-the-Loop
- terminology, Dialog Systems in Detail
- distributed representations, Distributed Representations-Distributed Representations Beyond Words and Characters
- DL (see deep learning)
- document categorization, Text Classification
- (see also text classification)
- DS (data science), The End-to-End NLP Process, The Data Science Process-Microsoft Team Data Science Process
- Duolingo, NLP in the Real World
E
- Economic News Article Tone and Relevance dataset (Figure Eight), One Pipeline, Many Classifiers, Explaining Classifier Predictions with Lime
- Educational Testing Service (ETS), Handcrafted Feature Representations, Handcrafted Feature Representations
- DSL, Search in E-Commerce
- ELK stack, Monitoring
- ELMo, Universal Text Representations
- emojis, Handling emojis
- Enam, S. Zayd, Other Aspects
- enterprise search engines, Search and Information Retrieval, A Typical Enterprise Search Pipeline-A Typical Enterprise Search Pipeline
- Ernst & Young, Accounting and auditing
- ETS (Educational Testing Service), Handcrafted Feature Representations, Handcrafted Feature Representations
F
- memes on, Identifying Memes
- facets, Search in E-Commerce
- Falcon Web Framework, An Example Scenario
- false propaganda, Applications
- Fast Healthcare Interoperability Resources (FHIR) standard, Outcome prediction and best practices, Medical Information Extraction and Analysis
- (see also feature engineering)
- FHIR (Fast Healthcare Interoperability Resources) standard, Outcome prediction and best practices, Medical Information Extraction and Analysis
- figurative language, Ambiguity
- Figure Eight, One Pipeline, Many Classifiers, Document Embeddings, Explaining Classifier Predictions with Lime, No Training Data
- filtering adult content, Applications
- formalism, Unique Challenges
G
- Gehrmann, Sebastian, Fake News
- KPE with, Implementing KPE
- GloVe , Pre-trained word embeddings, Word Embeddings, Deep Learning for Text Classification, Text Representation for SMTD
- Goldberg, Yoav, Text Representation
- Word2vec model, Word Embeddings-Pre-trained word embeddings, SkipGram, SkipGram, Distributed Representations Beyond Words and Characters, Universal Text Representations, Word Embeddings, Text Representation for SMTD, An Example Scenario
- Google AI, Outcome prediction and best practices, Outcome prediction and best practices, Minimizing Technical Debt, Other Aspects
- Google Translate, NLP in the Real World, NLP Tasks, Ambiguity, Topics in Brief, Machine Translation, Using a Machine Translation API: An Example
- language identification, Applications
- grammar, Unique Challenges
H
- handcrafted feature representations, Handcrafted Feature Representations-Handcrafted Feature Representations
- Harvard University, Fake News
- chatbots in, Applications
- patient prioritization and billing, Patient Prioritization and Billing
- Heinzerling, Benjamin, Other Aspects
- Horowitz, Andreessen, E-Commerce and Retail
I
- IE (see information extraction)
- open, Approaches to RE, Approaches to RE
- intelligent machines, Peeking over the Horizon
- interactive learning, Rasa NLU
J
- Jordan, Jeff, E-Commerce and Retail
K
- key performance indicators (KPIs), A Pipeline for Building Text Classification Systems, Iterating Existing Models, Monitoring
- (see also topics)
- KPE (see keyphase extraction)
- KPIs (key performance indicators), A Pipeline for Building Text Classification Systems, Iterating Existing Models, Monitoring
- Kubernetes, An Example Scenario
L
- ambiguity in, Ambiguity-Ambiguity
- figurative, Ambiguity
- language identification, Applications
- latent Dirichlet allocation (LDA), Topic Modeling-Topic Modeling, Unsupervised approach, Latent attribute extraction from reviews
- LDA (latent Dirichlet allocation), Topic Modeling-Topic Modeling, Unsupervised approach, Latent attribute extraction from reviews
- leadership, Team
- interactive, Rasa NLU
- lemmatization, Stemming and lemmatization
- length of text, Unique Challenges
- LexRank, Understanding Aspects
- Lime, Interpreting Text Classification Models, Troubleshooting and Interpretability, Troubleshooting and Interpretability
- Lipton, Zachary, Why Deep Learning Is Not Yet the Silver Bullet for NLP
- long short-term memory networks (LSTMs), Long short-term memory, Deep Learning for Text Classification, LSTMs for Text Classification-LSTMs for Text Classification, Fake News
- LSTMs (long short-term memory networks), Long short-term memory, Deep Learning for Text Classification, LSTMs for Text Classification-LSTMs for Text Classification, Fake News
M
- (see also artificial intelligence)
- overview, Machine Learning, Deep Learning, and NLP: An Overview-Machine Learning, Deep Learning, and NLP: An Overview
- use cases, Machine Translation
- McKinsey & Company, Peeking over the Horizon
- medical care (see healthcare)
- METEOR, Intrinsic Evaluation
- Microsoft Research, An Example Scenario
- Milne, A.A., Text Classification
- misinformation, Fake News
- (see also fake news)
- MIT Sloan, Peeking over the Horizon
- ML (see machine learning)
- customization, Rasa NLU
- evaluation of, Peeking over the Horizon
- goodness of fit, Evaluation
- testing models, Troubleshooting and Interpretability, Troubleshooting and Interpretability-Troubleshooting and Interpretability
- Molnar, Christoph, Troubleshooting and Interpretability
- MT (see machine translation)
- multilingual writing, Unique Challenges
N
- n-grams, Bag of N-Grams
- Nadella, Satya, Advanced Processing
- named entity recognition (NER), An NLP Walkthrough: Conversational Agents, Advanced Processing, IE Tasks, Named Entity Recognition-Practical Advice
- Natural Language Processing (NLP), Preface
- case studies, An NLP Walkthrough: Conversational Agents-An NLP Walkthrough: Conversational Agents, Case Study-Case Study
- Natural Language Tool Kit (NLTK)
- lemmatization with, Stemming and lemmatization
- POS tagging, Advanced Processing
- stemming with, Stemming and lemmatization
- Rasa, Rasa NLU-Rasa NLU
- news: tagging, IE Applications
- NLTK (see Natural Language Tool Kit)
- NLU (see natural language understanding)
O
- Occam’s razor, Why Deep Learning Is Not Yet the Silver Bullet for NLP
- Olah, Christopher, Long short-term memory
- open IE, Approaches to RE, Approaches to RE
- opinion mining, Applications
P
- Parsey McParseface Tagger, Advanced Processing
- perplexity, Intrinsic Evaluation
- pharmacovigilance, Pharmacovigilance
- Porter Stemmer, Stemming and lemmatization
- pre-processing, System-Specific Error Correction-Advanced Processing, Building Your Model, Mental Healthcare Monitoring, The KDD Process
- predicting health outcomes, Outcome prediction and best practices-Outcome prediction and best practices
- product catalogs (see catalogs)
- (see also recommendations)
- propaganda, false, Applications
- PwC, Accounting and auditing
Q
R
- Rao, Delip, Other Aspects
- Rasa NLU, Rasa NLU-Rasa NLU
- recall, Intrinsic Evaluation
- (see also recommender systems)
- recommendations, Topics in Brief
- recommender systems, Recommender Systems for Textual Data-Practical Advice, A Case Study: Substitutes and Complements
- recurrent neural networks (RNNs), Recurrent neural networks, Universal Text Representations, Deep Learning for Text Classification, Direct attribute extraction
- relationship extraction (RE), Advanced Processing, IE Tasks, Relationship Extraction-RE with the Watson API
- approaches to, Approaches to RE-Approaches to RE
- unsupervised, Approaches to RE
- RNNs (recurrent neural networks), Recurrent neural networks, Universal Text Representations, Deep Learning for Text Classification, Direct attribute extraction
- Ruder, Sebastian, SkipGram
S
- sarcasm, Universal Text Representations
- self-attention, Transformers, Transformers
- sentiment analysis, An NLP Walkthrough: Conversational Agents, Applications, Sentiment Analysis-Sentiment Analysis
- supervised approach, Supervised approach
- testing, Troubleshooting and Interpretability
- Shakespeare, William, Information Extraction
- Shap, Troubleshooting and Interpretability
- Shenfeld, Daniel, Other Aspects
- shopping (see e-commerce and retail)
- SkipGram, SkipGram-SkipGram
- unique challenges, Unique Challenges-Unique Challenges
- lemmatization with, Stemming and lemmatization
- POS tagging, Advanced Processing
- speech recognition, An NLP Walkthrough: Conversational Agents, A Pipeline for Building Dialog Systems
- Stanford Natural Language Processing Group
- stemming, Stemming and lemmatization
- Sumo Logic, Monitoring
- synonym replacement, Data Acquisition
T
- t-distributed Stochastic Neighboring Embedding (t-SNE), Visualizing Embeddings-Visualizing Embeddings
- TensorFlow model analysis (TFMA), Troubleshooting and Interpretability, Troubleshooting and Interpretability
- testing, Troubleshooting and Interpretability, Troubleshooting and Interpretability-Troubleshooting and Interpretability
- text categorization, Text Classification
- (see also text classification)
- text classification, NLP Tasks, Text Classification-Practical Advice, A Typical Enterprise Search Pipeline
- CNNs for, CNNs for Text Classification-CNNs for Text Classification
- DL for, Deep Learning for Text Classification-Text Classification with Large, Pre-Trained Language Models
- interpreting models, Interpreting Text Classification Models-Explaining Classifier Predictions with Lime
- KPIs for, Monitoring
- with large, pre-trained language models, Text Classification with Large, Pre-Trained Language Models-Text Classification with Large, Pre-Trained Language Models
- LSTMs for, LSTMs for Text Classification-LSTMs for Text Classification
- pipeline for building systems, A Pipeline for Building Text Classification Systems-Using Existing Text Classification APIs
- with public datasets, One Pipeline, Many Classifiers-One Pipeline, Many Classifiers, Case Study: Corporate Ticketing
- simple, A Simple Classifier Without the Text Classification Pipeline-A Simple Classifier Without the Text Classification Pipeline
- with SVMs, Support Vector Machine-Support Vector Machine
- distributed representations, Distributed Representations-Distributed Representations Beyond Words and Characters
- textacy, Implementing KPE
- TFMA (TensorFlow model analysis), Troubleshooting and Interpretability, Troubleshooting and Interpretability
- tokenization
- (see also text classification)
- topic modeling, NLP Tasks, Machine Learning, Deep Learning, and NLP: An Overview, Topics in Brief, Topic Modeling-What’s Next?, Unsupervised approach
- use cases, What’s Next?-What’s Next?
- translation APIs, Using a Machine Translation API: An Example-Using a Machine Translation API: An Example
- trolling, Memes and Fake News
- troubleshooting, Troubleshooting and Interpretability-Troubleshooting and Interpretability
- truly intelligent machines, Peeking over the Horizon
- Tsinghua University, An Example Scenario
- Turing, Alan, Chatbots
- Turnitin, NLP in the Real World
U
- UCSF, Outcome prediction and best practices
V
- venture capital (VC) firms, Peeking over the Horizon
- vocabulary
- (see also chatbots)
W
- Wadhwani AI, Peeking over the Horizon
- Weizenbaum, Joseph, Chatbots
- Winograd Schema Challenge, Ambiguity
- WinoGrande dataset, Peeking over the Horizon
- Wittgenstein, Ludwig, Topics in Brief
- word vectors, SkipGram
- Word2vec model (Google), Word Embeddings-Pre-trained word embeddings, SkipGram, Distributed Representations Beyond Words and Characters, Universal Text Representations, Text Representation for SMTD
- training, SkipGram
- WordNetLemmatizer, Stemming and lemmatization
X
Y
Z
Fair Use Sources
Natural Language Processing (NLP): What Is Language, Text classification, Language modeling, Google Gemini, ChatGPT
Machine Learning for NLP NLP ML, NLP DL - NLP Deep learning - Python NLP, NLP MLOps, Python NLP (sci-kit NLP, OpenCV NLP, TensorFlow NLP, PyTorch NLP, Keras NLP, NumPy NLP, NLTK NLP, SciPy NLP, sci-kit learn NLP, Seaborn NLP, Matplotlib NLP), C++ NLP, C# NLP, Golang NLP, Java NLP, JavaScript NLP, Julia NLP, Kotlin NLP, R NLP, Ruby NLP, Rust NLP, Scala NLP, Swift NLP, NLP history, NLP bibliography, NLP glossary, NLP topics, NLP courses, NLP libraries, NLP frameworks, NLP GitHub, NLP Awesome list. (navbar_nlp - See also navbar_llm, navbar_chatbot, navbar_dl, navbar_ml, navbar_chatgpt, navbar_ai)
Artificial Intelligence (AI): The Borg, SkyNet, Google Gemini, ChatGPT, AI Fundamentals, AI Inventor: Arthur Samuel of IBM 1959 coined term Machine Learning. Synonym Self-Teaching Computers from 1950s. Experimental AI “Learning Machine” called Cybertron in early 1960s by Raytheon Company; ChatGPT, Generative AI, NLP, GAN, AI winter, The Singularity, AI FUD, Quantum FUD (Fake Quantum Computers), AI Propaganda, Quantum Propaganda, Cloud AI (AWS AI, Azure AI, Google AI-GCP AI-Google Cloud AI, IBM AI, Apple AI), Deep Learning (DL), Machine learning (ML), AI History, AI Bibliography, Manning AI-ML-DL-NLP-GAN Series, AI Glossary, AI Topics, AI Courses, AI Libraries, AI frameworks, AI GitHub, AI Awesome List. (navbar_ai - See also navbar_dl, navbar_ml, navbar_nlp, navbar_chatbot, navbar_chatgpt, navbar_llm)
© 1994 - 2024 Cloud Monk Losang Jinpa or Fair Use. Disclaimers
SYI LU SENG E MU CHYWE YE. NAN. WEI LA YE. WEI LA YE. SA WA HE.