Skip to main content

Learn Skills Tools Games Exams Newsletter Community

Learn Skills Tools Games Exams Newsletter Community Search

AI From Scratch/Phase 05/Lesson 11/~75 minutes

Machine Translation

BuildPython

Translation is the task that paid for NLP research for thirty years and keeps paying now.

Back to phaseNLP — Foundations to Advanced Next lessonText Summarization

Phase 05

NLP — Foundations to Advanced

01Text Processing — Tokenization, Stemming, Lemmatization 02Bag of Words, TF-IDF, and Text Representation 03Word Embeddings — Word2Vec from Scratch 04GloVe, FastText, and Subword Embeddings 05Sentiment Analysis 06Named Entity Recognition 07POS Tagging and Syntactic Parsing 08CNNs and RNNs for Text 09Sequence-to-Sequence Models 10Attention Mechanism — The Breakthrough 11Machine Translation 12Text Summarization 13Question Answering Systems 14Information Retrieval and Search 15Topic Modeling — LDA and BERTopic 16Text Generation Before Transformers — N-gram Language Models 17Chatbots — Rule-Based to Neural to LLM Agents 18Multilingual NLP 19Subword Tokenization — BPE, WordPiece, Unigram, SentencePiece 20Structured Outputs & Constrained Decoding 21Natural Language Inference — Textual Entailment 22Embedding Models — The 2026 Deep Dive 23Chunking Strategies for RAG 24Coreference Resolution 25Entity Linking & Disambiguation 26Relation Extraction & Knowledge Graph Construction 27LLM Evaluation — RAGAS, DeepEval, G-Eval 28Long-Context Evaluation — NIAH, RULER, LongBench, MRCR 29Dialogue State Tracking

Loading lesson page...

Progress

0 / 29 phase lessons0%

Continue target

Phase 05

NLP — Foundations to Advanced

01Text Processing — Tokenization, Stemming, Lemmatization 02Bag of Words, TF-IDF, and Text Representation 03Word Embeddings — Word2Vec from Scratch 04GloVe, FastText, and Subword Embeddings 05Sentiment Analysis 06Named Entity Recognition 07POS Tagging and Syntactic Parsing 08CNNs and RNNs for Text 09Sequence-to-Sequence Models 10Attention Mechanism — The Breakthrough 11Machine Translation 12Text Summarization 13Question Answering Systems 14Information Retrieval and Search 15Topic Modeling — LDA and BERTopic 16Text Generation Before Transformers — N-gram Language Models 17Chatbots — Rule-Based to Neural to LLM Agents 18Multilingual NLP 19Subword Tokenization — BPE, WordPiece, Unigram, SentencePiece 20Structured Outputs & Constrained Decoding 21Natural Language Inference — Textual Entailment 22Embedding Models — The 2026 Deep Dive 23Chunking Strategies for RAG 24Coreference Resolution 25Entity Linking & Disambiguation 26Relation Extraction & Knowledge Graph Construction 27LLM Evaluation — RAGAS, DeepEval, G-Eval 28Long-Context Evaluation — NIAH, RULER, LongBench, MRCR 29Dialogue State Tracking

On this page

Resources

Costa-jussà et al. (2022). No Language Left Behind: Scaling Human-Centered Machine TranslationReading Post (2018). A Call for Clarity in Reporting BLEU ScoresReading Popović (2015). chrF: character n-gram F-score for automatic MT evaluationReading Hugging Face MT guideReading Artifact Mt EvaluatorSkill