Where are you going

Three types of transformers: Encoder model, decoder model, and sequence-to-sequence model — We are in the golden age of natural language processing. Since 2018, the born of GPT and BERT, a gang of transformers has emerged and gradually become the workhorse in industry. The star players of large language models are shown in the following figure:

Synthetic text data to the rescue — Annotation is expensive. The lack of training data and the imbalanced datasets are common issues in natural language processing projects. This article introduces some widely used augmentation approaches and provides example code for generating synthetic text data. Outline: Common approaches in test data augmentation: NLPAug, imbalanced-learn How to generate synthetic…

Inspiring thoughts about life’s hardest moments — The death of loved ones is one of life’s hardest moments. When it happened, most of us are unprepared. There are six TED talks that inspired me in answering questions about death including: Other than a biological process, can we redefine death from other perspectives? Is it possible that humans…

The novel interpretation of economic growth — The Chip 4 plan has become a trending topic globally. Why countries such as South Korea and the US can produce 3-nanometer chips while others can’t? Why it is extremely difficult to copy the technology to other countries? The book “Why Information Grows: The Evolution of Order, from Atoms to…

Intelligent search with pg_trgm and Levenshtein distance in Postgres — There are three common scenarios in database searches that go beyond the capability of traditional wildcard querying. First, when users search for “pet food” but there are no products called “pet food” found in your database, would the database be smart enough to return “cat food” or “dog food” instead? …

The Polaris in the technological society — Shrek has been working for a tech company for a few years. He is hard-working, self-motivated, and focused. But he still has lots of confusion about goals and reality, frustrations and pleasures, reason and instincts, sufferings and fruitfulness. Therefore he starts looking for answers in philosophy. What did philosophers think…

A grocery store achieved 22 million orders last year. Somehow you are the owner of this grocery store (congratulations 😊). You might want to ask some questions to build a deeper understanding of the underlying logic in your retail business. For example, within the large volume of transactions, What is…

Boost sales with machine learning and statistics powered recommender system — To buy, or not to buy: that is the question. If you were a manager of a grocery store, what products customers never bought but may like? If you run a restaurant, what is the food clients never ordered but may like? …