Teacher since June 2025
Nadia Haddad
Practical NLP: from tokens and embeddings to classification, translation and speech
9
tutors built
4.5Sample
average from 22 reviews
470Sample
lessons taught by their tutors
About Nadia
I teach natural language processing as a craft: turning messy text in many languages into something a model can use, and checking honestly whether the result works. I grew up switching between Arabic, French and English, and my work has been on text and speech systems that had to serve speakers of more than one language, so I notice quickly when a method quietly assumes English. My lessons mix small hands on examples with discussion of where things go wrong: tokenisers that split names badly, sentiment models that miss sarcasm, translations that sound fluent and are wrong. I keep explanations plain and I always show a simple baseline before anything fancy.
Knows about
Tutors by Nadia
9 tutors
Named entity recognition in practice
Extract people, places, organisations and custom entities from text, and evaluate the results properly79 lessonsSampleNadia Haddad$7Text classification from baseline to transformerText classification from baseline to transformer
Build text classifiers step by step, starting with a strong simple baseline and honest metrics74 lessonsSampleNadia Haddad$5Word and sentence embeddingsWord and sentence embeddings
Understand how meaning becomes vectors, compute similarity yourself and choose embeddings wisely74 lessonsSampleNadia Haddad$5Machine translation: how it works and failsMachine translation: how it works and fails
Understand how machines translate, judge translation quality and know when a human translator is needed74 lessonsSampleNadia Haddad$6Sentiment analysis done carefullySentiment analysis done carefully
Measure opinions in text without fooling yourself about sarcasm, mixed views or skewed averages59 lessonsSampleNadia Haddad$4Tokenisation: how text becomes numbersTokenisation: how text becomes numbers
See how models split text into tokens, why it matters for cost and context, and where it trips up56 lessonsSampleNadia HaddadFreeSpeech to text pipelinesSpeech to text pipelines
Turn recordings into accurate, timestamped transcripts and understand where speech recognition fails54 lessonsSampleNadia Haddad$5NLP for multilingual and low resource languagesNLP for multilingual and low resource languages
Build and evaluate language technology for languages that most datasets and models leave behindNadia Haddad$7Topic discovery and text clusteringTopic discovery and text clustering
Find themes in large text collections and check that the topics you found are real and usefulNadia Haddad$7Recent reviews
What students said about Nadia's tutors.
- Lin Y.Sample
Error analysis by cause was new to me. Half our 'model errors' were inconsistent labels.
- Selin K.Sample
The back translation example with gender neutral Turkish was exactly my situation. I now get a bilingual colleague to check key paragraphs.
- Carmen V.Sample
The baseline lesson was humbling. Our TF-IDF model came within two points of the expensive one we had been planning to buy.
- Patrick N.Sample
Very practical. The label guidelines lesson felt slow at first but it turned out to be where most of our problems were.
- Mohammed K.Sample
Computing cosine by hand removed the magic in a good way. The lesson on testing models with our own queries saved us from picking by leaderboard.
- Abdullah H.Sample
Useful and honest about accents. Our Arabic and English interviews really do get different accuracy, and now I measure it.