Skip to main content

FNLP - top navigation

  • Learn
  • Piazza
  • DRPS

Breadcrumb

  1. Home
  2. FNLP: Foundations of Natural Language Processing
  3. FNLP: Course Materials
  4. FNLP: Week 7: Discourse Semantics and Lexical Semantics

FNLP: 20: Lexical Semantics 1

Compositional semantics is a method for deriving the logical form of a sentence from its syntax tree.  But that logical form tells you very little about the denotations of its predical symbols: e.g., the word "dog" is mapped to dog(x), and all that reveals is that being a dog is a property of an individual.  It doesn't tell you commonsense information about dogs: that they're animals, people keep them as pets, they're mammals, they're furry, they have four legs and two ears etc etc.  All that kind of information is really important in NLP, because it contributes to commonsense inference that is critical in any adequate model of natural language understanding.  Accordingly, we will spend the next few sessions studying word meaning: how an individual word can have multiple senses, and how those senses are sometimes related to one another, and (critically) how some of those senses are largely predictable, because they are the product of generative mechanisms in the lexicon.  This folder consists of:
  • three videos of short lectures. They cover:
    1. Lexical Semantics: word senses, relations and classes
    2. Lexical Semantics: The Generative Lexicon
    3. Word Sense Disambiguation
  • some required reading from Jurafsky and Martin
  • a quiz that tests your understanding of the material presented here.
Please do the required reading, and attempt the quiz.  If there is anything you don't understand, then please ask questions in the lecture or on piazza.

Lecture 20 Slides: Whole!

  • 20_slides.pdf
20a: Lexical Semantics: Word senses, relations and classes
  • Slides: 20a_slides.pdf


20b: Lexical Semantics: The Generative Lexicon
  • Slides: 20b_slides.pdf


20c: Word Sense Disambiguation
  • Slides: 20c_slides.pdf 
     

Recommended Reading

J&M 23.1--23.5  (2nd edition Chapters 19.1--19.3 and 20.1--20.3).

NOTE: The abbreviation J&M refers to the textbook: 
Dan Jurafsky and James H. Martin, Speech and Language Processing.

When we specify 2nd edition, we are referring to the version of the book that was published by Pearson International in 2008.

When we specify 3rd edition, then we will supply links to the drafts of the relevant parts of that book (since the third editiion isn't published yet, but the current draft is available here).

 

Quiz: Lexical Semantics I

These questions are designed to test your understanding of the above course content; doing this quiz does not contribute to your overall grade.  Some questions require a text answer.  You can ask for formative feedback on these from your tutor or on piazza.  Other questions are multiple choice or they require a numeric answer: you will get immediate feedback for these. Please don't attempt this quiz until you have acquainted yourself with this lecture and the required reading.

You must be logged onto Learn to do this quiz.

 

License
All rights reserved The University of Edinburgh

Book traversal links for FNLP: 20: Lexical Semantics 1

  • FNLP: 19: Discourse
  • Up
  • FNLP: 21: Lexical Semantics 2 - Distributional Semantics

Navigation links

  • FNLP: Resource List
  • FNLP: Assessment
  • FNLP: Course Materials
    • FNLP: Week 1: Overview, Ambiguity and Corpora
    • FNLP: Week 2: Annotation, Evaluation and Language Models
    • FNLP: Week 3: Important ML techniques for NLP
    • FNLP: Week 4: More ML methods, Morphology and POS tagging
    • FNLP: Week 5: POS Tagging, Context Free Grammars and Parsing
    • FNLP: Week 6: More Parsing and Compositional Semantics
    • FNLP: Week 7: Discourse Semantics and Lexical Semantics
      • FNLP: 19: Discourse
      • FNLP: 20: Lexical Semantics 1
      • FNLP: 21: Lexical Semantics 2 - Distributional Semantics
    • FNLP: Week 8: Deep Learning for NLP
    • FNLP: Week 9: Neural Text Generation
    • FNLP Week 10: Transfer learning, Revision and Q&A
  • FNLP: Lab Exercises
  • FNLP: Tutorial Exercises
RSS feed

Opencourse privacy & accessibility statements; contact Informatics, ILTS.