An organized collection of 94 articles with NLP tips
Language models, transformers, embeddings, chatbots, knowledge graphs, etc.
Hello fellow NLP enthusiasts! This article provides an overview of the topics covered on NLPlanet since its inception and it’s meant to be a resource for learning about interesting NLP topics. At the end, I will give a brief overview of the growth of NLPlanet. Enjoy! 😄
Topics covered on NLPlanet
I’ve grouped the articles into distinct NLP and artificial intelligence categories. As some articles belong to multiple categories, you may find them more than once in the list.
Intro to NLP
- 33 important NLP tasks explained
- 21 popular NLP libraries of 2022
- The Basic Concepts and Terms You Need to Know for AI and ML
- 18 High-Quality Resources for studying NLP
- 21 Learning Resources for Text Classification
- 20 Learning Resources for Word Embeddings
- 20 Learning Resources for Transformers
- 20 Learning Resources for Information Retrieval
- 23 Learning Resources for Chatbots
- 18 Learning Resources for Language Models
- 19 Learning Resources for Question Answering
Intro to NLP tasks
- Quick intro to Text Style Transfer
- Quick intro to Text Simplification
- Quick intro to Question Answering
- Quick Intro to Sentiment Analysis
- 10 Surveys About Popular NLP Areas
- Quick Intro to Coreference Resolution with NeuralCoref
- Python Regular Expressions cheatsheet
- Quick Intro to Knowledge Base Question Answering
- Four different approaches to Text Summarization
- How to measure Commonsense Reasoning
Embeddings
- 11 word embeddings models you should know
- 20 Learning Resources for Word Embeddings
- Doc2Vec in a nutshell
- Learn TF-IDF with easy examples
- Topic Modeling and Semantic Search with Top2Vec
- Using Word2Vec to learn node embeddings on graphs
- Sentence Transformers cheat sheet
Language models
- A brief timeline of NLP from Bag of Words to the Transformer family
- Better Language Model Scaling for Downstream Tasks
- Unified Text-to-Text Tasks with T5
- A Full Guide to Finetuning T5 for Text2Text and Building a Demo with Streamlit
- Scaling Laws for Neural Language Models
- Making Large Language Models reason with Chain of Thought Prompting
- Scaling Transformers with Sparsity
- 18 Learning Resources for Language Models
- Gopher Language Model performance in a nutshell
- The OpenAI WebGPT model that answers questions browsing the web
- How the DeepMind RETRO model decouples reasoning and memorization
- Most used Decoding Methods for Language Models
- OpenAI InstructGPT brings Reward Models to GPT-3
- BERT finetuning with Hugging Face and training visualizations with TensorBoard
- Switch Transformers and huge sparse language models
- Ethical and social risks from Large Language Models
- Perplexity explained with simple probabilities
Knowledge graphs, entity linking, relation extraction
- Building a Knowledge Base from Texts: a Full Practical Example
- Visualize Dependency Parsing and Entities with displaCy
- A simple taxonomy of Knowledge Graph research
- Quick Intro to Knowledge Base Question Answering
- 11 applications of Knowledge Graphs
- Explainable AI with Knowledge Graphs
- Easy document annotation with Wikipedia concepts
- Relation Extraction with OpenNRE
Semantic search
- Semantic Search with Few Lines of Code
- 20 Learning Resources for Information Retrieval
- Quick tips to make your semantic search projects painless
- Semantic search of images with CLIP and Unsplash
- Topic Modeling and Semantic Search with Top2Vec
Metrics and benchmarks
- Popular NLP Benchmarks [Part 1]
- Keeping track of information and the LAMBADA benchmark
- Learn the BLEU metric by examples
- Learn the ROUGE metric by examples
- Perplexity explained with simple probabilities
- Intro to Word Error Rate (WER) for Speech-to-Text
- GLUE Tasks and 2022 Leaderboard
- SuperGLUE Tasks and 2022 Leaderboard
Explainable AI
- Explainable AI with Knowledge Graphs
- Explain predictions with SHAP values
- Explain predictions with LIME
- Partial Dependence and ICE Plots
Popular NLP libraries
- 21 popular NLP libraries of 2022
- SpaCy cheat sheet
- NLTK cheatsheet
- Quick Introduction to Haystack
- Keyword and keyphrase extraction with PKE
- Keyword and keyphrase extraction with KeyBERT
- Explain predictions with SHAP values
- Explain predictions with LIME
- Beginner intro to Hugging Face main classes and functions
- Sentence Transformers cheat sheet
Attention and Transformers
- Visualizing Seq2seq Models with Attention
- Visualizing Global vs Local Attention
- Scaling Transformers with Sparsity
- 20 Learning Resources for Transformers
Chatbots and Intents
- Building a Personal Assistant from Scratch
- 23 Learning Resources for Chatbots
- Effective intents identification in short texts with unsupervised learning
Sentiment Analysis
Paraphrases
Text Classification
- A Taxonomy of Data Augmentation for Text Classification
- 21 Learning Resources for Text Classification
- Basic taxonomy of Topic Tagging models and elementary use cases
- BERT finetuning with Hugging Face and training visualizations with TensorBoard
Streamlit
- Building a Knowledge Base from Texts: a Full Practical Example
- A Full Guide to Finetuning T5 for Text2Text and Building a Demo with Streamlit
Topic Modeling
Speech Recognition
- Building a Personal Assistant from Scratch
- Speech Recognition options with Python
- Intro to Word Error Rate (WER) for Speech-to-Text
Text to Speech
Grammar
Statistics
Training visualization
Multimodal models
- What DALL·E Mini Thinks of IT Workers
- Semantic search of images with CLIP and Unsplash
- Building a meme creation pipeline with CLIP and GPT-3
Ethics
Regular Expressions
Coreference resolution
Grammatical error correction
Tokenization
Question Answering
- Quick intro to Question Answering
- 19 Learning Resources for Question Answering
- Quick Intro to Knowledge Base Question Answering
- Quick Introduction to Haystack
Keyword and keyphrase extraction
Model optimizations
MLOps
- A Quick Intro to MLOps
- Using MLflow for Reproducible Data Science Experiments
- Training a PyTorch Model on GCP Vertex AI
- Deploy a PyTorch Model with Flask on GCP Vertex AI
PyTorch
JAX
Graphs
Recommender Systems
On writing about NLP
The current state of NLPlanet
NLPlanet started in December 2021 and currently has 617 followers on Medium, 1339 on LinkedIn, 117 on Twitter, and 281 members on its Discord server.
Here is the total number of daily views of the articles published on the Medium publication, which is on a low-but-steady growth.
We’re organizing some informal online meetups on the Discord server where members of the community give brief presentations about NLP topics and get to know each other. Up to now, we talked about topic modeling, speech recognition, speech analysis, and audio.
What’s next
You can expect NLPlanet to continue publishing articles that spread knowledge about NLP, at a rate between one to three articles per week.
If you’re interested in connecting with people in the same field worldwide, join the Discord server! 🙂