defter*
defter / katalog / EEE 586
EEE 586

Statistical Foundations of Natural Language Processing

Introduction to Natural Language Processing (NLP). Review of linguistic preliminaries. Review of mathematical foundations. Linguistic preprocessing: tokenization, lemmatization, Part-of-Speech (PoS) tagging, stop words. Hypothesis testing. Statistical estimators in the context of NLP. Evaluation measures. Collocations, n-gram models, word-sense disambiguation. Lexical semantics. Vector space models. Word embeddings. Hidden Markov Models (HMMs) and PoS tagging. Selective applications of NLP and relation of NLP to computational social science.

Credit3
ECTS5
BölümElectrical and Electronics Engineering
FacultyFaculty of Engineering

Hocalar 0 bu dönem · 1 geçmiş

Geçmişte ders veren (1 kişi)
Aykut Koç

→ STARS müfredatı / syllabus

Materyal — 0 dosya

Bu derste henüz materyal yok.

İlk dosyayı sen ekleyebilirsin — notlar, geçmiş finaller, çözümler, cheat-sheet, ne varsa. Drive linki / PDF / ZIP / fotoğraf, hepsi olur.

Şu an: mail at, ben düzenleyip yayına alayım. Form/upload UX yakında geliyor (Kimya tasarlıyor).

↑ konuya EEE 586 yaz

Müfredat detayı STARS syllabus

📚 Önerilen kaynaklar

  • Önerilen Speech and Language Processing Daniel Jurafsky and James H. Martin · 2018 (online) · Prentice Hall
  • Önerilen Foundations of Statistical Natural Language Processing Christopher D. Manning and Hinrich Schutze · 1999 · The MIT Press

⚖️ Değerlendirme

  • 30% — Project: Assignments (×3)
  • 35% — Term project: Term Project (×1)
  • 35% — Final: Final (×1)

⚠️ FZ engelleyen şartlar

No FZ will be assigned.

📅 Haftalık müfredat

Introduction/overview for Natural Language Processing and Computational Linguistics Review of Mathematical Foundations Review of Linguistic Foundations Linguistic Preprocessing Hypothesis Testing, statistical estimators, evaluation measures Collocations, n-gram models, word-sense disambiguation Collocations, n-gram models, word-sense disambiguation Neural language models Neural language models Lexical semantics Vector space models Word embeddings Selective Applications of Natural Language Processing, Examples of Computational Social Science Selective Applications of Natural Language Processing, Examples of Computational Social Science ECTS - Workload Table: Activities Number Hours Workload Preparation for the presentation 1 3 3 Preparation for Final exam 1 30 30 Project Presentation 1 1 1 Project 1 47 47 Final exam 1 3 3 Midterm exam 1 2 2 Preparation for Midterm exam 1 20 20 Course hours 14 3 42 Project Interview 1 2 2 Total Workload: 150 Total Workload / 30: 150 / 30 5 ECTS Credits of the Course: 5 Type of Course: Lecture Teaching Methods: Lecturing - Independent study