Docsity
Docsity

Prepare for your exams
Prepare for your exams

Study with the several resources on Docsity


Earn points to download
Earn points to download

Earn points by helping other students or get them with a premium plan


Guidelines and tips
Guidelines and tips

Lexical Semantics: Understanding Word Meanings in Natural Language Processing, Exercises of Painting

A lecture note from the Foundations of Natural Language Processing (FNLP) course, specifically Lecture 14, which focuses on lexical semantics. The lecture discusses the importance of understanding word meanings in building a question answering system and introduces various challenges in lexical semantics, such as word senses, synonyms, hyponyms, and polysemy. The lecture also presents WordNet as a solution to some of these problems.

Typology: Exercises

2021/2022

Uploaded on 09/12/2022

attourney
attourney 🇬🇧

3.8

(11)

228 documents

1 / 43

Toggle sidebar

This page cannot be seen from the preview

Don't miss anything!

bg1
Foundations of Natural Language Processing
Lecture 14
Lexical Semantics:
Word senses, relations, and classes
Alex Lascarides
(slides by Lascarides, Schneider, Koehn, Goldwater)
6 March 2020
Alex Lascarides FNLP Lecture 14 6 March 2020
pf3
pf4
pf5
pf8
pf9
pfa
pfd
pfe
pff
pf12
pf13
pf14
pf15
pf16
pf17
pf18
pf19
pf1a
pf1b
pf1c
pf1d
pf1e
pf1f
pf20
pf21
pf22
pf23
pf24
pf25
pf26
pf27
pf28
pf29
pf2a
pf2b

Partial preview of the text

Download Lexical Semantics: Understanding Word Meanings in Natural Language Processing and more Exercises Painting in PDF only on Docsity!

Foundations of Natural Language Processing

Lecture 14

Lexical Semantics:

Word senses, relations, and classes

Alex Lascarides (slides by Lascarides, Schneider, Koehn, Goldwater)

6 March 2020

Alex Lascarides FNLP Lecture 14 6 March 2020

Meaning

  • One grand goal of artificial intelligence is to understand what people mean when they talk.
  • But how do we know if we succeeded?

What is meaning? What is understanding?

  • These are deep philosophical questions
  • NLP usually takes a more pragmatic view: can the computer behave as though it understands (in order to do what we want)?
    • Dialogue systems (e.g., Eliza)
    • Machine translation
    • Question answering
  • What issues will we face in building such systems?

A Concrete Goal

  • We would like to build
    • a machine that answers questions in natural language.
    • may have access to knowledge bases
    • may have access to vast quantities of English text
  • Basically, a smarter Google
  • This is typically called Question Answering

Why is lexical semantics important for building such a system?

Example Question

  • Question

When was Barack Obama born?

  • Text available to the machine

Barack Obama was born on August 4, 1961

  • This is easy.
    • just phrase a Google query properly: "Barack Obama was born on *"
    • syntactic rules that convert questions into statements are straight-forward

Example Question (2)

  • Question

What plants are native to Scotland?

  • Text available to the machine

A new chemical plant was opened in Scotland.

  • What is hard?
    • words may have different meanings (senses)
    • we need to be able to disambiguate between them

Example Question (4)

  • Question

Which animals love to swim?

  • Text available to the machine

Polar bears love to swim in the freezing waters of the Arctic.

  • What is hard?
    • words can refer to a subset (hyponym) or superset (hypernym) of the concept referred to by another word
    • we need to have database of such A is-a B relationships, called an ontology

Example Question (5)

  • Question

What is a good way to remove wine stains?

  • Text available to the machine

Salt is a great way to eliminate wine stains

  • What is hard?
    • words may be related in other ways, including similarity and gradation
    • we need to be able to recognize these to give appropriate responses

WordNet

  • Some of these problems can be solved with a good ontology, e.g., WordNet
  • WordNet (English) is a hand-built resource containing 117,000 synsets: sets of synonymous words (See http://wordnet.princeton.edu/)
  • Synsets are connected by relations such as
    • hyponym/hypernym (IS-A: chair-furniture)
    • meronym (PART-WHOLE: leg-chair)
    • antonym (OPPOSITES: good-bad)
  • globalwordnet.org now lists wordnets in over 50 languages (but variable size/quality/licensing)

Word Sense Ambiguity

  • One word form, same category, but more than one sense (homonyms):

I put my money in the bank. vs. He rested at the bank of the river. I like playing squash vs. I like drinking squash

  • More generally, words can have multiple (related or unrelated) senses
  • Words often exhibit sense ambiguities that fall into (semi-)predictable patterns (polysemy): see next slides (from Hugh Rabagliati in PPLS).

29

30

How many senses?

  • 5 min. exercise: How many senses does the word interest have?

How many senses?