Download presentation
Presentation is loading. Please wait.
1
Lecture 21 Computational Lexical Semantics
CSCE Natural Language Processing Lecture 21 Computational Lexical Semantics Topics Features in NLTK III Computational Lexical Semantics Semantic Web USC Readings: NLTK book Chapter 10 Text Chapters 20 April 3, 2013
2
Overview Readings: Text 19,20 NLTK Book: Chapter 10
Last Time (Programming) Features in NLTK NL queries SQL NLTK support for Interpretations and Models Propositional and predicate logic support Prover9 Today Last Lectures slides 25-29 Computational Lexical Semantics Readings: Text 19,20 NLTK Book: Chapter 10 Next Time: Computational Lexical Semantics II
3
Model Building in NLTK - Chapter 10continued
Mace model builder lp = nltk.LogicParser() # install Mace4 config_mace4('c:\Python26\Lib\site-packages\prover9') a3 = lp.parse('exists x.(man(x) & walks(x))') c1 = lp.parse('mortal(socrates)') c2 = lp.parse('-mortal(socrates)') mb = nltk.Mace(5) print mb.build_model(None, [a3, c1]) True print mb.build_model(None, [a3, c2]) print mb.build_model(None, [c1, c2]) False
4
>>> a4 = lp. parse('exists y. (woman(y) & all x
>>> a4 = lp.parse('exists y. (woman(y) & all x. (man(x) -> love(x,y)))') >>> a5 = lp.parse('man(adam)') >>> a6 = lp.parse('woman(eve)') >>> g = lp.parse('love(adam,eve)') >>> mc = nltk.MaceCommand(g, assumptions=[a4, a5, a6]) >>> mc.build_model() True
5
10.4 The Semantics of English Sentences
Principle of compositionality --
6
Representing the λ-Calculus in NLTK
(33) a. (walk(x) ∧ chew_gum(x)) b. λx.(walk(x) ∧ chew_gum(x)) c. \x.(walk(x) & chew_gum(x)) -- the NLTK way!
7
Lambda0.py import nltk from nltk import load_parser lp = nltk.LogicParser() e = lp.parse(r'\x.(walk(x) & chew_gum(x))') print e \x.(walk(x) & chew_gum(x)) e.free() print lp.parse(r'\x.(walk(x) & chew_gum(y))') \x.(walk(x) & chew_gum(y))
8
Simple β-reductions >>> e = lp.parse(r'\x.(walk(x) & chew_gum(x))(gerald)') >>> print e \x.(walk(x) & chew_gum(x))(gerald) >>> print e.simplify() [1] (walk(gerald) & chew_gum(gerald))
9
Predicate reductions >>> e3 = lp.parse('\P.exists x.P(x)(\y.see(y, x))') >>> print e3 (\P.exists x.P(x))(\y.see(y,x)) >>> print e3.simplify() exists z1.see(z1,x)
10
Figure 19.7 Inheritance of Properties
Exists e,x,y Eating(e) ^ Agent(e, x) ^ Theme(e, y) “hamburger edible?” from wordnet Speech and Language Processing, Second Edition Daniel Jurafsky and James H. Martin Copyright ©2009 by Pearson Education, Inc. Upper Saddle River, New Jersey 07458 All rights reserved.
11
Figure 20.1 Possible sense tags for bass
Chapter 20 – Word Sense disambiguation (WSD) Machine translation Supervised vs unsupervised learning Semantic concordance – corpus with words tagged with sense tags
12
Feature Extraction for WSD
Feature vectors Collocation [wi-2, POSi-2, wi-1, POSi-1, wi, POSi, wi+1, POSi+1, wi+2, POSi+2] Bag-of-words – unordered set of neighboring words Represent sets of most frequent content words with membership vector [0,0,1,0,0,0,1] – set of 3rd and 7th most freq. content word Window of nearby words/features
13
Naïve Bayes Classifier
w – word vector s – sense tag vector f – feature vector [wi, POSi ] for i=1, …n Approximate by frequency counts But how practical?
14
Looking for Practical formula
. Still not practical
15
Naïve == Assume Independence
Now practical, but realistic?
16
Training = count frequencies
. Maximum likelihood estimator (20.8)
17
Decision List Classifiers
Naïve Bayes hard for humans to examine decisions and understand Decision list classifiers - like “case” statement sequence of (test, returned-sense-tag) pairs
18
Figure 20.2 Decision List Classifier Rules
19
WSD Evaluation, baselines, ceilings
Extrinsic evaluation - evaluating embedded NLP in end-to-end applications (in vivo) Intrinsic evaluation – WSD evaluating by itself (in vitro) Sense accuracy Corpora – SemCor, SENSEVAL, SEMEVAL Baseline - Most frequent sense (wordnet sense 1) Ceiling – Gold standard – human experts with discussion and agreement
20
Figure 20.3 Simplified Lesk Algorithm
gloss/sentence overlap
21
Simplified Lesk example
The bank can guarantee deposits will eventually cover future tuition costs because it invests in adjustable rate mortgage securities.
22
SENSEVAL competitions
Check the Senseval-3 website.
23
Corpus Lesk weights applied to overlap words inverse document frequency idfi = log (Ndocs / num docs containing wi)
24
20.4.2 Selectional Restrictions and Preferences
25
Wordnet Semantic classes of Objects
26
Minimally Supervised WSD: Bootstrapping
Yarowsky algorithm Heuritics: one sense per collocations one sense per discourse
27
Figure 20.4 Two senses of plant
28
Figure 20.5
29
Figure 20.6 Path Based Similarity
30
Figure 20.6 Path Based Similarity
. \ simpath(c1, c2)= 1/pathlen(c1, c2) (length + 1)
31
Information Content word similarity
32
Figure 20.7 Wordnet with P(c) values
33
Figure 20.8
35
Figure 20.9
36
Figure 20.10
37
Figure 20.11
38
Figure 20.12
39
Figure 20.13
40
Figure 20.14
41
Figure 20.15
42
Figure 20.16
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.