BLOG Archives

What is BERTScore – Bidirectional Encoder Representations from Transformers Score?
Gallery

What is BERTScore – Bidirectional Encoder Representations from Transformers Score?

Lois Angelo Dar Juan2025-07-03T06:03:55+00:00

BERTScore (Bidirectional Encoder Representations from Transformers Score) Cheat Sheet BERTScore is an effective evaluation metric that looks beyond surface-level word matching to assess the meaning behind the generated text. Instead of counting overlapping words like traditional metrics such as BLEU or ROUGE, BERTScore taps into the power of pre-trained transformer models (like BERT) to compare the semantic similarity between tokens in the generated output and a reference sentence. It does this by calculating the cosine similarity between their contextual embeddings. Initially proposed by Zhang et al. (2020), BERTScore has quickly become a popular choice in natural language processing tasks where [...]

What is BERTScore – Bidirectional Encoder Representations from Transformers Score?Lois Angelo Dar Juan2025-07-03T06:03:55+00:00

What is Retrieval Augmented Generation (RAG) in Machine Learning?
Gallery

What is Retrieval Augmented Generation (RAG) in Machine Learning?

Nikee Tomas2025-06-30T03:46:57+00:00

Retrieval-Augmented Generation (RAG) Cheat Sheet Retrieval-Augmented Generation (RAG) is a method that enhances large language models (LLMs) outputs by incorporating information from external, authoritative knowledge sources. Instead of relying solely on pre-trained data, RAG retrieves relevant content at inference time to ground its responses. LLMs (Large Language Models) are trained on massive datasets and use billions of parameters to perform tasks like: Question answering Language translation Text completion RAG extends LLM capabilities to domain-specific or private organizational knowledge without requiring model retraining. It provides a cost-efficient way to improve the relevance, accuracy, and utility of LLM outputs in dynamic or [...]

What is Retrieval Augmented Generation (RAG) in Machine Learning?Nikee Tomas2025-06-30T03:46:57+00:00

What is Metric for Evaluation of Translation with Explicit ORdering?
Gallery

What is Metric for Evaluation of Translation with Explicit ORdering?

Ace Kenneth Batacandulo2025-06-29T17:01:03+00:00

When evaluating machine translations, assessing how closely the translation matches a human's understanding is essential. METEOR (Metric for Evaluation of Translation with Explicit ORdering) is an evaluation metric that provides a more comprehensive and accurate measurement of translation quality. Unlike traditional metrics like BLEU, METEOR considers precision and recall and the semantic meaning of words and their order in a sentence, offering a more nuanced and reliable translation evaluation. In this article, we'll delve deeper into METEOR, how it works, and why it's used to evaluate machine translation quality. Additionally, we'll provide an easy-to-understand cheat sheet that summarizes its features. [...]

What is Metric for Evaluation of Translation with Explicit ORdering?Ace Kenneth Batacandulo2025-06-29T17:01:03+00:00

Simplifying DNS Management: How to Transfer Your Domain’s DNS from GoDaddy to Amazon Route 53
Gallery

Simplifying DNS Management: How to Transfer Your Domain’s DNS from GoDaddy to Amazon Route 53

Jodi Gabano2025-06-29T10:45:34+00:00

If you have ever tried to create a website and wanted it to be accessible through a custom web address, then you have already touched the basics of DNS, or Domain Name System. DNS is what connects your domain name to the actual server where your website lives. It plays a critical role in making sure your site is reachable, fast, and secure for users around the world. Many website owners start by registering their domain with a provider like GoDaddy. This works well for buying and setting up a domain quickly. However, as your project or business grows, [...]

Simplifying DNS Management: How to Transfer Your Domain’s DNS from GoDaddy to Amazon Route 53Jodi Gabano2025-06-29T10:45:34+00:00

Azure OpenAI
Gallery

Azure OpenAI

Nestor Mayagma Jr.2025-07-01T08:41:06+00:00

Azure OpenAI Cheat Sheet Azure OpenAI offers access to OpenAI’s powerful models (e.g., GPT-4o, GPT-4 Turbo, GPT-3.5 Turbo, DALL-E, Whisper) with robust security and compliance for enterprises. Hosted on Microsoft Azure, allows for seamless integration with various Azure services and tools. Key Concepts Model Deployment: You must deploy a model (e.g., gpt-4, gpt-35-turbo) to your Azure resource before using it. Quota Types: Dynamic Quota: Shared pool for flexible consumption. Provisioned Throughput Units (PTUs): Dedicated capacity for predictable performance. Content Filtering: Built-in safety system to detect and block harmful content. Prompt Engineering: Crafting effective prompts to guide model behavior. Supported Models [...]

Azure OpenAINestor Mayagma Jr.2025-07-01T08:41:06+00:00

Google Veo 3: The Latest Breakthrough in AI Video Generation
Gallery

Google Veo 3: The Latest Breakthrough in AI Video Generation

Lois Angelo Dar Juan2025-06-26T08:35:57+00:00

Artificial intelligence has come a long way from its early days when it could only do simple tasks like solving math problems, playing basic games, or following step-by-step instructions from programmers. Back then, AI relied on fixed rules and couldn’t learn or improve on its own. As technology advanced, AI became more capable and useful. It learned to recognize voice commands, identify faces, suggest videos based on viewing habits, and learn patterns from data. These examples show how AI moved beyond strict programming and started making smart decisions on its own, thanks to machine learning and deep learning. Over time, [...]

Google Veo 3: The Latest Breakthrough in AI Video GenerationLois Angelo Dar Juan2025-06-26T08:35:57+00:00

Why I Chose AWS Lambda to Power My App’s Cloud Logic
Gallery

Why I Chose AWS Lambda to Power My App’s Cloud Logic

Marc Hendri Soquiat2025-06-27T09:40:37+00:00

For this article, I will demonstrate how I used AWS Lambda as an all-around backend system for a mock-up mobile application I developed for my Design subject in school. The mobile application is an IoT application that integrates communication between a mobile device and a handheld barcode scanner using a Bluetooth module. It also includes security functions, such as code decryption and user statuses. For the dependencies, I used flutter_blue, get, and http. The list below indicates the use cases of AWS Lambda for my mobile application. I hope, by the end of this article, you will know how to [...]

Why I Chose AWS Lambda to Power My App’s Cloud LogicMarc Hendri Soquiat2025-06-27T09:40:37+00:00

What is Area Under the ROC Curve (AUC) in Machine Learning?
Gallery

What is Area Under the ROC Curve (AUC) in Machine Learning?

Nestor Mayagma Jr.2025-07-01T02:38:28+00:00

Area Under the ROC Curve (AUC) Cheat Sheet AUC, short for Area Under the Curve of the Receiver Operating Characteristic (ROC), is a metric that evaluates how well a model can differentiate between different classes. A performance metric primarily used for binary classification models. Ranges from 0 to 1: 1: Perfect model. 0.5: Model performs no better than random guessing. 0: Model inversely ranks positives and negatives. Accurate Outcomes True Positive (TP): The model predicted 1, which matches the actual result. True Negative (TN): The model predicted 0, and the real outcome was also 0. Misclassified Outcomes False Positive (FP): [...]

What is Area Under the ROC Curve (AUC) in Machine Learning?Nestor Mayagma Jr.2025-07-01T02:38:28+00:00

What is BiLingual Evaluation Understudy (BLEU) Score for Machine Translation?
Gallery

What is BiLingual Evaluation Understudy (BLEU) Score for Machine Translation?

Nikee Tomas2025-06-25T01:15:03+00:00

BiLingual Evaluation Understudy (BLEU) Score Cheat Sheet BLEU (BiLingual Evaluation Understudy) is a corpus-level metric designed to automatically evaluate the quality of machine-generated text, most commonly in machine translation (MT). It compares n-gram overlap between the machine’s output and one or more human reference translations. Introduced by Papineni et al. (2002), BLEU became the first automated metric to correlate highly with human judgments in large-scale MT evaluations. It remains a widely used baseline for evaluating machine-generated text. Common Use Cases The BLEU score is widely used in natural language processing tasks that require comparing machine-generated text to human-written references. Its primary [...]

What is BiLingual Evaluation Understudy (BLEU) Score for Machine Translation?Nikee Tomas2025-06-25T01:15:03+00:00

What is RLHF – Reinforcement Learning from Human Feedback?
Gallery

What is RLHF – Reinforcement Learning from Human Feedback?

Irene Bonso2025-06-24T05:52:27+00:00

What is Reinforcement Learning from Human Feedback (RLHF)? A technique to improve AI models using human feedback to guide learning. Builds on reinforcement learning, where AI learns by trial and error to achieve goals. Uses human opinions to determine good or bad outputs, enhancing traditional reward systems. How RLHF Works Data Collection: AI generates multiple outputs (e.g., answers or text snippets). Humans provide feedback by ranking or comparing outputs (e.g., which is better or more helpful). Supervised Fine-Tuning: Model is trained with human feedback to produce preferred outputs. Establishes a baseline for good responses. Building a Reward Model: Creates a [...]

What is RLHF – Reinforcement Learning from Human Feedback?Irene Bonso2025-06-24T05:52:27+00:00