What is ROUGE Metrics – Recall-Oriented Understudy for Gisting Evaluation?
Recall-Oriented Understudy for Gisting Evaluation (ROUGE) Cheat Sheet ROUGE is a family of metrics designed to assess the similarity between machine-generated text (candidate) and human-written reference text (ground truth) in NLP tasks like text summarization and machine translation. Measures how well generated text captures key information and structure from reference text, emphasizing recall (proportion of relevant information preserved). Score Range: 0 to 1, where higher scores indicate greater similarity between candidate and reference texts. [...]
Creating an AI Chatbot with LangChain for FREE (No API Keys, No Tokens)
Creating an AI Chatbot with LangChain for FREE (No API Keys, No Tokens) The Big Question: Can You Build AI Without Breaking the Bank? We asked ourselves a simple question: Can you build a chatbot without using any paid API at all? Most tutorials on AI chatbots start the same way: "First, grab your OpenAI API key and add your credit card..." But what if you don't have one? Or don't want to use [...]
Beginner Guide to Building a Hate Speech Classifier with BERT
You've seen the warnings: "This comment may violate our community guidelines," or you've watched online posts or videos get flagged and removed due to their hate speech content. This means that the platform is already using models to detect harmful content. However, have you ever questioned how these models work? How are these models able to understand human sarcasm, cultural slang, and even multilingual language in one sentence? In this guide, we'll walk through the [...]
Motoko vs Solidity: A Developer-Centric Comparison
Motoko vs Solidity: A Developer-Centric Comparison A New Era in Smart Contract Development Innovative contract development has evolved significantly over the past decade. With the rise of decentralized finance (DeFi), non-fungible tokens (NFTs), and a growing ecosystem of decentralized applications, Solidity has long been the standard for writing contracts on the Ethereum Virtual Machine (EVM). It introduced developers to a new paradigm: trustless systems, which do not require trust between parties, programmable money, and [...]
“Hello, [User]!”: A Beginner’s Guide to Building an AI Chatbot with Google Gemini API and Next.js
These days, it feels like there’s an AI chatbot for everything. Need help with homework? Stuck on a coding problem? Want to research a random topic? These virtual assistants can answer just about any general question you throw at them. They’re becoming our go-to partners for learning, creating, and problem-solving. But have you ever wanted a chatbot that doesn't just give generic answers but understands and responds with information specific to your needs? [...]
Launching an Amazon EC2 Instance using Terraform
What's up, Dojos! This is your first step on automating your cloud infrastructure by launching an EC2 Instance using Terraform! Efforts from various cloud providers such as AWS made managing your configurations manageable and easy by the use of their Management Consoles. With AWS, launching an EC2 instance, setting up IAM configurations, and VPC provisioning have never been easier within their console. But what if you have to configure large amounts of resources? Provisioning [...]
Your First Look into Generative AI: What It Is and Why It Matters
Your First Look into Generative AI: What It Is and Why It Matters Generative artificial intelligence, or Genb AI, has quickly become a powerful force that is changing many industries. It can write, draw, make music, create videos, and even generate code. These tools easily adjust to different creative and practical tasks, promoting innovation and original ideas across various fields. So, what is Generative AI? How does it work, where is it making a [...]
What is BERTScore – Bidirectional Encoder Representations from Transformers Score?
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 [...]
What is Retrieval Augmented Generation (RAG) in Machine Learning?
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 [...]
What is Metric for Evaluation of Translation with Explicit ORdering?
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 [...]