Adding more links to various categories and sections: NLP, Things to …

…know, Visualisation, Time series, Data, Graph and many others. Also links to two new Newsletters.
bikashdaga · Jul 16, 2021 · 7b764b7 · 7b764b7
1 parent 1866218
commit 7b764b7
Show file tree

Hide file tree

Showing 10 changed files with 110 additions and 30 deletions.
diff --git a/README-details.md b/README-details.md
@@ -42,14 +42,29 @@
 - [Automated machine learning tools (or partial AutoML tools)](./things-to-know.md#automated-machine-learning-tools-or-partial-automl-tools)
 - [Automated Machine Learning - Google search results](https://www.google.com/search?ei=b3ktXKfbEqWAjLsPqdOxiAs&q=automated+machine+learning&oq=automated+machine&gs_l=psy-ab.3.0.0j0i20i263j0l5j0i20i263j0l2.187330.192290..193008...3.0..0.70.1100.20......0....1..gws-wiz.....6..35i39j0i131j0i67.2o6PTTxjJjw)
 - [Recipes for Driverless AI](https://github.com/h2oai/driverlessai-recipes)
-- [PyCaret Tutorial Using Titanic Dataset](https://www.kaggle.com/ravileo/pycaret-tutorial-using-titanic-dataset](https://towardsdatascience.com/announcing-pycaret-an-open-source-low-code-machine-learning-library-in-python-4a1f1aad8d46)
-- [PyCaret Demo](https://pycaret.org/demo/](https://github.com/pycaret/pycaret-demo-dataraction)
-- [Running Low on Time? Use PyCaret to Build your Machine Learning Model in Seconds](https://www.analyticsvidhya.com/blog/2020/05/pycaret-machine-learning-model-seconds/?utm_source=feed&utm_medium=feed-articles&utm_campaign=feed)
-- Libra • Automates the end-to-end machine learning process in just one line of code: [GitHub](https://lnkd.in/g4kYRnq) | [Notebooks with tutorials](https://lnkd.in/g95uKnR) | [Docs](https://lnkd.in/g_vF72M) | [NLP Queries](https://lnkd.in/gZhufPf) 
+- PyCaret
+  + [PyCaret Tutorial Using Titanic Dataset](https://www.kaggle.com/ravileo/pycaret-tutorial-using-titanic-dataset](https://towardsdatascience.com/announcing-pycaret-an-open-source-low-code-machine-learning-library-in-python-4a1f1aad8d46)
+  + [PyCaret Demo](https://pycaret.org/demo/](https://github.com/pycaret/pycaret-demo-dataraction)
+  + [Write and train your own custom machine learning models using PyCaret](https://towardsdatascience.com/write-and-train-your-own-custom-machine-learning-models-using-pycaret-8fa76237374e)
+  + [Running Low on Time? Use PyCaret to Build your Machine Learning Model in Seconds](https://www.analyticsvidhya.com/blog/2020/05/pycaret-machine-learning-model-seconds/?utm_source=feed&utm_medium=feed-articles&utm_campaign=feed)
++ Libra • Automates the end-to-end machine learning process in just one line of code: [GitHub](https://lnkd.in/g4kYRnq) | [Notebooks with tutorials](https://lnkd.in/g95uKnR) | [Docs](https://lnkd.in/g_vF72M) | [NLP Queries](https://lnkd.in/gZhufPf) 
 - [GitHub is the best AutoML you will ever need 👇 👇 👇](https://www.linkedin.com/posts/profile-moez_github-is-the-best-automl-you-will-ever-need-activity-6696949164791652352-bleJ)
 - [AutoGOAL: an autoML framework (high & low level) by Alejandro Piad et al.](https://www.linkedin.com/posts/madewithml_machinelearning-artificialintelligence-madewithml-activity-6693165741547626496-mHhS)
 - [OttoML - Otto makes machine learning an intuitive, natural language experience.](https://github.com/KartikChugh/Otto)
 - [TPOT for Automated Machine Learning in Python](https://machinelearningmastery.com/tpot-for-automated-machine-learning-in-python/)
+- Abacus AI workshops
+  + [Classification](https://colab.research.google.com/drive/1Rajb3bHw45k4PWvDlxsQNCd3j5WuHbIm#forceEdit=true&sandboxMode=true&scrollTo=0D9QEgVs6Ni0)
+  + [Regression](https://bit.ly/RE_regression)
+  + [Forecasting and Recommendations](https://colab.research.google.com/drive/1AnYlxBWo2UUJv5zh7UUbi1YYGwiAmoxl?usp=sharing#scrollTo=__NDm8-bYCqx)
+  - [Workshop on Explainable ML: The code  used to create the Input versus Output visualisation](https://www.youtube.com/watch?v=fGOcvtVaY18)
+- [How to Use AutoKeras for Classification and Regression](https://machinelearningmastery.com/autokeras-for-classification-and-regression)
+| [AutoKeras Website](https://autokeras.com/)
+- Snorkel: Interact with the modern ML stack by programmatically building and managing training datasets: [Snorkel Superglue](https://github.com/HazyResearch/snorkel-superglue) | [Author page](https://ajratner.github.io/)
+- [Build machine learning powered applications without a data scientist](https://telepath.io/)
+- [A delightful machine learning tool that allows you to train/fit, test and use models without writing code](https://github.com/nidhaloff/igel)
+- [Automated Machine Learning (AutoML) Libraries for Python](https://machinelearningmastery.com/automl-libraries-for-python/)
+- [Auto sklearn](https://github.com/automl/auto-sklearn)
+- [OpenML](https://openml.org)
 
 ### Ethics / altruistic motives
 
@@ -149,6 +164,7 @@ See [Mathematics, Statistics, Probability & Probabilistic programming](./details
   + [Graph Programming by Uri Valevski https://bit.ly/3nhZr4w](https://www.linkedin.com/posts/towards-data-science_graph-programming-by-uri-valevski-https-activity-6718600830007742464-Ehy5)
   + [Open Graph Benchmark: Datasets for Machine Learning on Graphs -](https://www.linkedin.com/posts/philipvollet_machinelearning-datascience-analytics-activity-6715867835287109633-Y_MN)
   - [BCS APSG - 2019 02 14 How Graph Technology is Changing AI and ML at BCS London](https://www.youtube.com/watch?v=oMqP3ISPWBY)
+  - [Language Generation with Multi-hop Reasoning on Commonsense Knowledge Graph](https://www.linkedin.com/posts/philipvollet_datascience-nlp-pytorch-activity-6734350662294917120-LSsw)
   - [Graph databases](./data/README.md#databases)
     - See the [Grakn example](./examples/data/databases/graph/grakn/README.md) in the `examples/data/databases/graph/grakn` folder
 

diff --git a/data/databases.md b/data/databases.md
@@ -37,6 +37,7 @@
 - [Universal Invariant and Equivariant Graph Neural Networks](https://www.linkedin.com/posts/eric-feuilleaubois-ph-d-43ab0925_universal-invariant-and-equivariant-graph-activity-6636212749133246464-_xqf)
 - [Auto-Generated KG](https://www.linkedin.com/posts/bo-li-8503b896_auto-generated-knowledge-graphs-activity-6637543428051828736-jVdT)
 - [Graph Convolutional Neural Networks for Molecule Generation | NTU Graph Deep Learning Lab](https://www.linkedin.com/posts/eric-feuilleaubois-ph-d-43ab0925_graph-convolutional-neural-networks-for-molecule-activity-6640244313009737728-IdCP)
+- [Modelling the Time-of-Arrival Using Distributions](https://www.inovex.de/blog/time-of-arrival-distributions/)
 
 ## Tools, packages and frameworks
 - [PyTorch Geometric Temporal is a temporal (dynamic) extension library for PyTorch Geometric](https://github.com/benedekrozemberczki/pytorch_geometric_temporal)
@@ -45,6 +46,7 @@
 - [GraphScope is a unified distributed graph computing platform](https://www.linkedin.com/posts/philipvollet_datascience-analytics-bigdata-activity-6793219722117820417-vhSv)
 - [Tweeki - Linking Named Entities on Twitter to a Knowledge Graph](https://www.linkedin.com/posts/philipvollet_twitter-data-datascience-activity-6733786978178990080-ZiD3)
 
+
 ## Misc.
 - [Difference between JOIN and UNION in SQL](https://www.geeksforgeeks.org/difference-between-join-and-union-in-sql/)
 - [Difference between COMMIT and ROLLBACK in SQL](https://www.geeksforgeeks.org/difference-between-commit-and-rollback-in-sql/)

diff --git a/data/model-analysis-interpretation-explainability.md b/data/model-analysis-interpretation-explainability.md
@@ -21,29 +21,13 @@
 - [What-if-tool on GitHub](https://github.com/PAIR-code/what-if-tool)
 - [useR2020! Keynote: "Responsible Automation: Towards Interpretable & Fair AutoML"](https://github.com/ledell/useR2020-automl)
 - [Explainable AI by IBM](https://github.com/Trusted-AI/AIX360) | [GitHub](https://github.com/IBM/lale) | [(video, slides, codes) on youtube channel](https://www.youtube.com/channel/UCj09XsAWj-RF9kY4UvBJh_A) | [GitHub](https://github.com/decentdilettante)
-SHAP (SHapley Additive exPlanations) is a game theoretic approach to explain the output of any machine learning model. 
-https://www.linkedin.com/posts/philipvollet_machinelearning-datascience-technology-activity-6732555181315227648-NPD1
-
-Intro to Explainable AI
-https://www.linkedin.com/posts/activity-6679735518781153280-RewD
-
-Gradio! You can now generate interpretations with one line of code! 
-https://www.linkedin.com/posts/philipvollet_machinelearning-python-datascience-activity-6730046018248962048-Icgv
-
-LIME for auditing black-box models
-https://towardsdatascience.com/lime-for-auditing-black-box-models-b97d6d2580b4?gi=95ed4978e936
-
-Interpretable Machine Learning - Christoph Molnar 
-https://www.youtube.com/watch?v=0LIACHcxpHU&t=3533s
-
-AI Ethics, Fairness, Explainability: Q&A and discussion at this session:
-code lab: https://github.com/decentdilettante/XAI
-10:33:08     https://github.com/Trusted-AI/AIX360
-10:33:19     https://github.com/IBM/lale
-10:39:20    ["Conversational Processes and Causal Explanation" by Hilton:](https://pdfs.semanticscholar.org/5093/4979694fb48e55d0cf38888f67b84ad6601b.pdf
-
-Tech talk: Explainable anomaly detection
-https://www.youtube.com/watch?v=0p8o3uj96Uc&feature=push-u-sub&attr_tag=ccXKOv7Gba4BJCOf%3A6
+- [SHAP (SHapley Additive exPlanations) is a game theoretic approach to explain the output of any machine learning model](https://www.linkedin.com/posts/philipvollet_machinelearning-datascience-technology-activity-6732555181315227648-NPD1)
+- [Intro to Explainable AI](https://www.linkedin.com/posts/activity-6679735518781153280-RewD)
+- [Gradio! You can now generate interpretations with one line of code!](https://www.linkedin.com/posts/philipvollet_machinelearning-python-datascience-activity-6730046018248962048-Icgv)
+- [LIME for auditing black-box models](https://towardsdatascience.com/lime-for-auditing-black-box-models-b97d6d2580b4?gi=95ed4978e936)
+- [Interpretable Machine Learning - Christoph Molnar](https://www.youtube.com/watch?v=0LIACHcxpHU&t=3533s)
+- AI Ethics, Fairness, Explainability: Q&A and discussion at this session: [code lab](https://github.com/decentdilettante/XAI) | [Trusted-AI](https://github.com/Trusted-AI/AIX360) | [lale](https://github.com/IBM/lale) | ["Conversational Processes and Causal Explanation" by Hilton](https://pdfs.semanticscholar.org/5093/4979694fb48e55d0cf38888f67b84ad6601b.pdf) | [Tech talk: Explainable anomaly detection](https://www.youtube.com/watch?v=0p8o3uj96Uc&feature=push-u-sub&attr_tag=ccXKOv7Gba4BJCOf%3A6)
+- [With the library "explainerdashboard" you can visually analyze the predictions of your #ml models](https://www.linkedin.com/posts/inna-vogel-nlp_ml-nlp-ai-activity-6770064375039463424-2LkQ)
 
 ## Articles, blog posts, papers, notebooks, books, presentations
 

diff --git a/natural-language-processing/README.md b/natural-language-processing/README.md
@@ -1,6 +1,6 @@
 # Natural Language Processing (NLP)
 
-Better NLP: [![Better NLP](https://img.shields.io/docker/pulls/neomatrix369/better-nlp.svg)](https://hub.docker.com/r/neomatrix369/better-nlp) 
+Better NLP: [![Better NLP](https://i§g.shields.io/docker/pulls/neomatrix369/better-nlp.svg)](https://hub.docker.com/r/neomatrix369/better-nlp) 
 
 NLP Java: [![NLP Java](https://img.shields.io/docker/pulls/neomatrix369/nlp-java.svg)](https://hub.docker.com/r/neomatrix369/nlp-java) | NLP Clojure: [![NLP Clojure](https://img.shields.io/docker/pulls/neomatrix369/nlp-clojure.svg)](https://hub.docker.com/r/neomatrix369/nlp-clojure) | NLP Kotlin: [![NLP Kotlin](https://img.shields.io/docker/pulls/neomatrix369/nlp-kotlin.svg)](https://hub.docker.com/r/neomatrix369/nlp-kotlin) | NLP Scala: [![NLP Scala](https://img.shields.io/docker/pulls/neomatrix369/nlp-scala.svg)](https://hub.docker.com/r/neomatrix369/nlp-scala) | <br/>
 NLP using DL4J (cuda): [![NLP using DL4J (cuda)](https://img.shields.io/docker/pulls/neomatrix369/dl4j-nlp-cuda.svg)](https://hub.docker.com/r/neomatrix369/dl4j-nlp-cuda)
@@ -13,6 +13,7 @@ NLP using DL4J (cuda): [![NLP using DL4J (cuda)](https://img.shields.io/docker/p
 - [Library, Framework, Models, Tools, Services](#library-framework-models-tools-services)
 - [Metaphor detection](#metaphor-detection)
 - [Sentiment analysis](#sentiment-analysis)
+- [Topic modelling](#topic-modelling)
 - [Presentations](#presentations)
 - [Notebooks](#notebooks)
 - [Unstructured to structured data](#unstructured-to-structured-data)
@@ -60,6 +61,11 @@ See [Metaphor detection](./metaphor-detection.md)
 
 See [Sentiment analysis](./sentiment-analysis.md)
 
+## Topic modelling
+
+- [Topic Modeling in Python using PyCaret ☟](https://www.linkedin.com/feed/update/urn:li:activity:6768428905800982528/)
+- [Topic modeling helps discover abstract topics](https://www.linkedin.com/posts/srivatsan-srinivasan-b8131b_machinelearning-datascience-ml-activity-6744246884703059968-DyNX)
+
 ## Presentations
 
 - [Natural Language Processing presentation by Ovidiu S.](../presentations/nlp/)
@@ -92,6 +98,7 @@ See [Sentiment analysis](./sentiment-analysis.md)
 ## Text data Augmentation
 
 - Easy Data Augmentation for Text Classification: [Video](https://www.youtube.com/watch?v=3w92peJtYNQ) | [Kernel](https://www.kaggle.com/init927/nlp-data-augmentation)
+- [SentAugment is a data augmentation technique for semi-supervised learning in NLP](https://www.linkedin.com/posts/philipvollet_datascience-machinelearning-pytorch-activity-6727834166941118464-bVIR)
 
 ## Summarise text
 

diff --git a/natural-language-processing/general.md b/natural-language-processing/general.md
@@ -63,6 +63,19 @@
 - [The #NLP Model Forge: Generate Model Code On Demand #AI - check out this overview by Matthew Mayo](https://www.kdnuggets.com/2020/08/nlp-model-forge.html#.X0PCodTTDeQ.linkedin)
 - [NLP as a service using Streamlit & FastAPI (Sebastián Ramírez Montaño) w/ Hugging Face transformers by Abhishek Kumar Mishra](https://www.linkedin.com/posts/madewithml_insight-made-with-ml-activity-6701484081949097984-NUsj)
 - [Project Insight is designed to create NLP as a service ](https://lnkd.in/g85xFCz)
+- [Language Generation with Multi-hop Reasoning on Commonsense Knowledge Graph](https://www.linkedin.com/posts/philipvollet_datascience-nlp-pytorch-activity-6734350662294917120-LSsw)
+- [Best Natural Language Processing competitions on @kaggle to learn from](https://youtube.com/watch?v=-nH4OSyjwSI)
+- [The biggest highlight of 𝗘𝗠𝗡𝗟𝗣 𝟮𝟬𝟮𝟬 𝗶𝘀 𝘁𝗵𝗲 "𝗛𝗶𝗴𝗵-𝗣𝗲𝗿𝗳𝗼𝗿𝗺𝗮𝗻𝗰𝗲 𝗡𝗮𝘁𝘂𝗿𝗮𝗹 𝗟𝗮𝗻𝗴𝘂𝗮𝗴𝗲 𝗣𝗿𝗼𝗰𝗲𝘀𝘀𝗶𝗻𝗴" tutorial by Google Research](https://www.linkedin.com/posts/ivan-bilan_nlp-machinelearning-deeplearning-activity-6736873867190513664-rsqz)
+- [Bort is an optimal subset of architectural parameters for the BERT architecture](https://www.linkedin.com/posts/philipvollet_nlp-machinelearning-datascience-activity-6727329794150813696-SFqV)
+- [sparknlp_display visualizations that power the 80+ #SparkNLP Streamlit demos](https://www.linkedin.com/posts/philipvollet_openpensource-sparknlp-nlp-activity-6734909712002904064-B_Ig
+)
+- [Deep learning pipeline for Natural Language Processing (NLP) by Bauyrjan Jyenis](https://buff.ly/32D7j82)
+- [Review of the Book “Natural Language Processing For Hackers”](https://tomassetti.me/review-of-the-book-natural-language-processing-for-hackers/)
+- [awesome-neural-adaptation-in-NLP](https://www.linkedin.com/posts/philipvollet_nlp-datascience-machinelearning-activity-6729376332976922624-si9O)
+- [Twitter Sentiment Analysis - Classical Approach vs Deep Learning as beginner friendly notebook](https://www.linkedin.com/posts/philipvollet_datascience-deeplearning-machinelearning-activity-6738353924371283968-59XV)
+- [A compilation of five excellent resources that could prove to be highly beneficial for people starting out in #NLP](https://www.linkedin.com/posts/parulpandeyindia_free-hands-on-tutorials-to-get-started-in-activity-6734443852297445376-lHby)
+- [An amazing article on "Cluster Documents Using Word2Vec"](https://lnkd.in/dEUUFnJ)
+- [Swiss NLP activities group](https://swissnlp.org/activities/)
 
 ### Transformers
 
@@ -84,7 +97,9 @@
 - [The broad potential of GPT-3 is not only related to pure language! It can program, design and maybe it will finally replace lawyers and makes the world a better place](https://www.linkedin.com/posts/philipvollet_nlp-gpt3-machinelearning-activity-6691640022606729216-Bsiv)
 - [The pain ends: English to Regex • Never search for regular expressions on StackOverflow again Powered by GPT-3](https://www.linkedin.com/posts/philipvollet_nlp-machinelearning-deeplearning-activity-6693043670670831616-tUhF)
 - [GPT-3 implementation of Q&A: chatbot conversations (Transformer implementation)](https://colab.research.google.com/drive/1wf6f96tDCWmo7lMEf-6PQxFk8yksKUkG?usp=sharing)
-
+- [How to use GPT-J, the open-source alternative to GPT-3 GPT-J demo](https://6b.eleuther.ai/)
+- [Builder a faster Search engine with Transformers and Haystack](https://datamuni.com/@shivanandroy/Building-a-faster-accurate-search-engine-with-transformers)
+- [Online tutorial on building production monitoring architectures for machine learning at scale](https://towardsdatascience.com/production-machine-learning-monitoring-outliers-drift-explainers-statistical-performance-d9b1d02ac158?gi=3f9f06e3bda1)
 
 ## Text generation
 

diff --git a/natural-language-processing/library-framework-models-tools-services.md b/natural-language-processing/library-framework-models-tools-services.md
@@ -68,6 +68,25 @@
 - [HMNI • Fuzzy Name Matching with Machine Learning. Perform common fuzzy name matching tasks including similarity scoring, record linkage, deduplication and normalization](https://www.linkedin.com/posts/philipvollet_nlp-machinelearning-datascience-activity-6694666551989297152-EGtw)
 - [Jina is an AI-powered search framework, empowering developers to create cross-/multi-modal search systems (e.g. text, images, video, audio) on the cloud](https://github.com/jina-ai/jina)
 - [Twint is an advanced Twitter scraping tool written in Python that allows for scraping Tweets from Twitter profiles without using Twitter's API](https://www.linkedin.com/posts/philipvollet_python-data-twitter-activity-6713352923373551616-GNlu)
+- [ProphetNet: MS's transformer variant](https://github.com/microsoft/ProphetNet)
+- [Rouge](https://pypi.org/project/rouge/)
+- [Pointer Generator](https://github.com/AIKevin/Pointer_Generator_Summarizer)
+- [Textract](https://textract.readthedocs.io/en/stable/python_package.html)
+- [Text Rank](https://www.analyticsvidhya.com/blog/2018/11/introduction-text-summarization-textrank-python/)
+- [TextHero](https://texthero.org/)
+- [Facebook Research • TaBERT a pre-trained language model for learning joint representations of natural language utterances and structured tables for semantic parsing](https://www.linkedin.com/posts/philipvollet_nlp-machinelearning-technology-activity-66861)
+- [SpikeX - SpaCy Pipes for Knowledge Extraction](https://www.linkedin.com/posts/philipvollet_nlp-machinelearning-datascience-activity-6790492432502026240-wVxj)
+- [Obsei: Observe SEgment and Inform - A workflow automation tool for text segmentation](https://www.linkedin.com/posts/philipvollet_datascience-nlp-machinelearning-activity-6748875008870875136-hQoh)
+- (X) Cross-Lingual Transfer Evaluation of Multilingual Encoders: 
+[site](https://sites.research.google/xtreme) | [github](https://github.com/google-research/xtreme)
+- [VecMap (cross-lingual word embedding mappings)](https://github.com/artetxem/vecmap)
+- [PyCaret: Natural Language Processing Module](https://pycaret.org/nlp/)
+- [NLPretext - a python with all the text preprocessing functions you need to ease your NLP project](https://www.linkedin.com/posts/kalyankatikapallisubramanyam_nlproc-nlp-machinelearning-activity-6821345994182070272-2La4)
+- [New release: Gramformer a framework for detecting, highlighting and correcting grammatical errors on natural language text](https://www.linkedin.com/posts/philipvollet_datascience-machinelearning-nlp-activity-6819547377955930112-mTye)
+- [Machine Learning and Deep Learning: EN-JP Lexicon](https://github.com/Machine-Learning-Tokyo/EN-JP-ML-Lexicon)
+- [MALLET is a Java-based package for statistical natural language processing, d](https://github.com/mimno/Mallet)
+- [Crowlingo Multilingual NLP](https://www.dataiku.com/product/plugins/crowlingo-nlp/)
+- [An adaptable platform for text analytics and discovery](http://www.rosette.com/)
 
 # Contributing