How to Write Better Prompts: A Case Study of Iterative Improvement
In the world of AI and NLP, the quality of a prompt can make or break the outcome. Crafting an effective prompt is an art that involves careful iteration and understanding the nuances of language models.
It also requires continuously refining your instructions. A well-crafted prompt can mean the difference between a vague response and a highly detailed, actionable output.
In this blog post, I want to share my journey of iteratively improving a prompt to achieve better summarization results for meeting notes written in Japanese. -->
Read More
A Guide to Nested Cross-Validation with Code Step by Step
Nested cross-validation is a powerful technique for evaluating the generalization performance of machine learning models, particularly useful when tuning hyperparameters.
It involves two layers of cross-validation: an outer loop for assessing the model's performance and an inner loop for hyperparameter tuning. -->
Read More
Making Emoji Clouds for Different Personalities
Hello, data enthusiasts and social media buffs! Ever wondered if our personality types influence the emojis we use in tweets? Let's embark on a delightful data journey to explore this connection.
We'll be using Python, some cool libraries, and a sprinkle of emoji magic to visualize how different MBTI personality types express themselves through emojis🚀 -->
Read More
Proposing a new function of a conversational search system that allows natural language communication with users: Searching for Love
The new function that I propose is called Searching for Love. The primary goal of Searching for Love is to provide users a tailored and interactive search process that goes beyond traditional dating platforms.
It utilizes conversational AI to engage users in meaningful conversations, understanding their preferences, values, and compatibility factors, and ultimately facilitate successful matches. -->
Read More
BERT VS. LSTM: Performances in Sentiment Classification
The objective of this post is to evaluate and compare the performance of 2 deep learning algorithms (BERT and LSTM) for conducting binary classification in sentiment analysis.
The evaluation will focus on two key metrics: accuracy, which measures the overall classification performance, and training time, which assesses the efficiency of each algorithm. -->
Read More
How to analyze your local dataset with Google Golab?
One the about using Colab that bothers me is that sometimes it is difficult to use when analyzing data file stored in your local environment.
In this post, I will show you a convenient way to prepare your local dataset ready for analysis on Colab. There are 5 steps in total. -->
Read More
