【NLP】01 Course Introduction

1. Question answering
2. Information Extraction
3. Information Extraction & Sentiment Analysis
4. Machine Translation
5. Language Technology

Ambiguity makes NLP hard:
“Crash blossrooms”

1. non-standard English
2. segmentation issues
3. idioms
4. neologisms
5. world knowledge
6. tricky entity names

Teaches key theory and methods for statistical NLP:

1. Viterbi
2. Naïve Bayes, Maxent classifiers
3. N-gram language modeling
4. Statistical Parsing
5. Inverted index, tf-idf, vector models of meaning

For pracIcal, robust real-world applications

1. Information extracIon
2. Spelling correction
3. Information retrieval
4. Sentiment analysis

Skills you’ll need:

1. Simple linear algebra(vectors,matrices)
2. Basic probability theory
3. Java or Python programming