IS 7118 Unit-9 Semantics

Unit-9: Semantics
IS 7118: Natural Language Processing

1st Year, 2nd Semester, M.Sc(IS)
(Slides are adapted from Text Book by Jurafsky & Martin )
Content
• Lexical Semantics
– Word Senses
– Relation between Senses
– Wordnet
• Computational Lexical Semantics
– Word similarity
• Thesaurus methods
• Distribution methods
IS 7118:NLP Unit-9: Semantics, 2

Prof.R.K.Rao Bandaru
Word Meaning and Similarity
Word Senses and Word Relations

Reminder: lemma and wordform
• A lemma or citation form

– Same stem, part of speech, rough semantics
• A wordform
– The “inflected” word as it appears in text
Wordform Lemma
banks bank
sung sing
duermes dormir
Lemmas have senses
• One lemma “bank” can have many meanings:

• …a bank can hold the investments in a
Sense 1:
custodial
1 account…
• “…as agriculture burgeons on the east
Sense 2: bank the river will shrink even more”
2
• Sense (or word sense)

– A discrete representation of an aspect of a word’s meaning.
• The lemma bank here has two senses

Meaning
• Traditionally, meaning in language has been studied from
three perspectives
– The meaning of a text or discourse

– The meanings of individual sentences or utterances
– The meanings of individual words

Lexical Semantics
• Lexical Semantics is the linguistic study of systematic meaning
related structure of lexemes
• A lexeme is an individual entry in the lexicon consisting of a pairing
of a particular form(orthographic or phonological) with a single
meaning representation.
• A lexicon is a finite set of lexems.
• A lexeme may have different meanings. A lexeme’s meaning
component is known as one of its senses.
• Sense is a discrete representation of an aspect of a word’s meaning.
– Different senses of the lexeme duck.
• an animal, to lower the head, ...
– Different senses of the lexeme yüz
• face, to swim, to skin, the front of something, hundred, ... 7
IS 7118:NLP Unit-9: Semantics,
Relations Among Lexemes and Their Senses
• Homonymy
• Polysemy
• Metonym
• Synonymy /Antonym
• Hyponymy /Hypernym
• Meronym/Holonym
• Troponym

Homonymy
Homonyms: words that share a same form but have unrelated, distinct
meanings:
– bank1: financial institution, bank2: sloping land
– bat1: club for hitting a ball, bat2: nocturnal flying mammal
1. Homographs (bank/bank, bat/bat)
2. Homophones:
a) Write and right
b) Piece and peace
• Homonymy causes problems for NLP applications:
1) Information retrieval
• “bat care”
2) Machine Translation
• bat: murciélago (animal) or bate (for baseball)
3) Text-to-Speech
• bass (stringed instrument) vs. bass (fish) 9
Polysemy
• Polysemy is the phenomenon of multiple related meanings
in a same lexeme.
1. The bank was constructed in 1875 out of local red brick.
2. I withdrew the money from the bank
– Are those the same sense?
• Sense 2: “A financial institution”
• Sense 1: “The building belonging to a financial institution”
• Most non-rare words have multiple meanings

• The number of meanings is related to its frequency
• Verbs tend more to polysemy
• Distinguishing polysemy from homonymy isn’t always easy (or necessary)
10
Metonymy
• Metonymy or Systematic Polysemy: A systematic relationship

between senses. A word that denotes one thing but refers to a
related thing. E.g. Washington is metonym for United States
Government; plastic is a metonym for credit card
• Lots of types of polysemy are systematic
– School, university, hospital
– All can mean the institution or the building.
• A systematic relationship:
– Building Organization
• Other such kinds of systematic polysemy:
Author (Jane Austen wrote Emma) Works of Author (I love Jane Austen)
Tree (Plums have beautiful blossoms) Fruit (I ate a preserved
plum)
11
How do we know when a word has more than
one sense?
• The “zeugma” test: Two senses of serve?
– Which flights serve breakfast?
– Does Lufthansa serve Philadelphia?
– ?Does Lufthansa serve breakfast and San Jose?
• Since this conjunction sounds weird,
– we say that these are two different senses of “serve”

Synonymy
• Synonymy is the phenomenon of two different lexemes having the
same meaning in some or all contexts.
– Big / large; Water / H20; couch / sofa; automobile / car; vomit / throw up
– In fact, one of the senses of two lexemes are same.
• Two lexemes are synonyms if they can be successfully substituted
for each other in all situations, we say they have the same
propositional meaning
– What does successfully mean?
• Preserves the meaning
• But may not preserve the acceptability based on notions of politeness, slang, ...
• Example - Big and large?
– That’s my *big sister a big plane I drink water
– That’s my large sister a large plane I drink H20
• Thus, synonymy is a relation between senses than words 13
• *older, or grown-up Prof.R.K.Rao Bandaru
Antonyms
• Senses that are opposites with respect to one feature of
meaning
• Otherwise, they are very similar!
dark/light short/longfast/slow
rise/fall
hot/cold up/down
in/out
• More formally: antonyms can
– define a binary opposition
or be at opposite ends of a scale
• long/short, fast/slow
– Be reversives:
• rise/fall, up/down
Hyponymy and Hypernymy
• One sense is a hyponym of another if the first sense is more
specific, denoting a subclass of the other
– car is a hyponym of vehicle
– mango is a hyponym of fruit
• Conversely hypernym/superordinate (“hyper is super”)

– vehicle is a hypernym of car
– fruit is a hypernym of mango
Superordinate/hyper vehicle fruit furniture

Subordinate/hyponym car mango chair

Hyponymy more formally
• Extensional: The class denoted by the superordinate extensionally
includes the class denoted by the hyponym
• Entailment: A sense A is a hyponym of sense B if being an A entails
being a B
• Hyponymy is usually transitive
– (A hypo B and B hypo C entails A hypo C)
• Another name: the IS-A hierarchy
– A IS-A B (or A ISA B)
– B subsumes A
• An instance is an individual, a proper noun that is a unique entity
• San Francisco is an instance of city
– But city is a class
• city is a hyponym of municipality...location...
Meronym/Holonym and Troponym
• Meronym:A word that names a part of a larger whole.
– X is a meronym of Y if X is a part of Y.
• E.g., wheel is a meronym of car; 'brim' and 'crown' are meronyms of 'hat'
• Holonym: A word that names the whole of which a given word is a
part.
– X is a holonym of Y if Ys are parts of Xs
• E.g., bike is a holonym of tire; car is a holonym of wheel
• Troponym: A word that denotes a manner of doing something.

– verb Y is a troponym of verb X if the activity Y is doing X in some manner
• E.g., March is troponym of walk; saunter is a troponym of walk

Lexical Resourses
• There are lots of lexical resources available
– Word lists
– On-line dictionaries
– Corpora
• The most ambitious one is WordNet
– A database of lexical relations for English
– Versions for other languages are under
development
– WordNet has both classes and instances.
WordNet and other Online

Thesauri
Applications of Thesauri and Ontologies
• Information Extraction
• Information Retrieval
• Question Answering
• Bioinformatics and Medical Informatics
• Machine Translation

WordNet 3.0
• A hierarchically organized lexical database

• On-line thesaurus + aspects of a dictionary
• Some other languages available or under development
– (Arabic, Finnish, German, Portuguese…)
Category Unique Strings

Noun 117,798
Verb 11,529
Adjective 22,479
Adverb 4,481
WordNet
Graph, where nodes

are words and edges
are relationships
There is some
hierarchical
information, for
example with
hyp-er/o-nomy

Senses of “bass” in Wordnet

How is “sense” defined in WordNet?
• The synset (synonym set), the set of near-synonyms,

instantiates a sense or concept, with a gloss
• Example: chump as a noun with the gloss:
“a person who is gullible and easy to take advantage of”
• This sense of “chump” is shared by 9 words:
chump1, fool2, gull1, mark9, patsy1, fall guy1, sucker1, soft touch1,
mug2
• Each of these senses have this same gloss
– (Not every sense; sense 2 of gull is the aquatic bird)

WordNet Hypernym Hierarchy for “bass”

WordNet –bass Hyponyms
Results for "Hyponyms (...is a kind of this), full" search of noun "bass"
6 of 8 senses of bass
Sense 2
bass, bass part -- (the lowest part in polyphonic music)
=> ground bass -- (a short melody in the bass that is constantly repeated)
=> thorough bass, basso continuo -- (a bass part written out in full and accompanied by figures for successive chords)
=> figured bass -- (a bass part in which the notes have numbers under them to indicate the chords to be played)
Sense 4
sea bass, bass -- (the lean flesh of a saltwater fish of the family Serranidae)
=> striped bass, striper -- (caught along the Atlantic coast of the United States)
Sense 5
freshwater bass, bass -- (any of various North American freshwater fish with lean flesh (especially of the genus Micropterus))
=> largemouth bass -- (flesh of largemouth bass)
=> smallmouth bass -- (flesh of smallmouth bass)
Sense 6
bass, bass voice, basso -- (the lowest adult male singing voice)
=> basso profundo -- (a very deep bass voice)
Sense 7
bass -- (the member with the lowest range of a family of musical instruments)
=> bass fiddle, bass viol, bull fiddle, double bass, contrabass, string bass --
(largest and lowest member of the violin family)
=> bass guitar -- (the lowest six-stringed guitar)
=> bass horn, sousaphone, tuba -- (the lowest brass wind instrument)
=> euphonium -- (a bass horn (brass wind instrument) that is the tenor of the tuba family)
=> helicon, bombardon -- (a tuba that coils over the shoulder of the musician)
=> bombardon, bombard -- (a large shawm; the bass member of the shawm family)
Sense 8
bass -- (nontechnical name for any of numerous edible marine and freshwater spiny-finned fishes)
=> freshwater bass -- (North American food and game fish)

WordNet – bass Synonyms
Results for "Synonyms, ordered by estimated frequency" search of noun "bass"
8 senses of bass
Sense 1
bass -- (the lowest part of the musical range)
=> low pitch, low frequency -- (a pitch that is perceived as below other pitches)
Sense 2
bass, bass part -- (the lowest part in polyphonic music)
=> part, voice -- (the melody carried by a particular voice or instrument in polyphonic music; "he tried to sing the tenor part")
Sense 3
bass, basso -- (an adult male singer with the lowest voice)
=> singer, vocalist, vocalizer, vocaliser -- (a person who sings)
Sense 4
sea bass, bass -- (the lean flesh of a saltwater fish of the family Serranidae)
=> saltwater fish -- (flesh of fish from the sea used as food)
Sense 5
freshwater bass, bass -- (any of various North American freshwater fish with lean flesh (especially of the genus Micropterus))
=> freshwater fish -- (flesh of fish from fresh water used as food)
Sense 6
bass, bass voice, basso -- (the lowest adult male singing voice)
=> singing voice -- (the musical quality of the voice while singing)
Sense 7
bass -- (the member with the lowest range of a family of musical instruments)
=> musical instrument, instrument -- (any of various devices or contrivances that can be used to produce musical tones or sounds)
Sense 8
bass -- (nontechnical name for any of numerous edible marine and freshwater spiny-finned fishes)
=> percoid fish, percoid, percoidean -- (any of numerous spiny-finned fishes of the order Perciformes)

WordNet Noun Relations

WordNet 3.0
• Where it is:
http://wordnetweb.princeton.edu/perl/webwn
• Libraries
– Python: WordNet from NLTK
http://www.nltk.org/Home
– Java:
• JWNL, extJWNL on sourceforge
IS 7118:NLP Unit-9: Semantics, Prof.R.K.Rao Bandaru

MeSH: Medical Subject Headings
thesaurus from the National Library of Medicine
• MeSH (Medical Subject Headings)
– 177,000 entry terms that correspond to 26,142
biomedical “headings”
Synset
• Hemoglobins
Entry Terms: Eryhem, Ferrous Hemoglobin, Hemoglobin
Definition: The oxygen-carrying proteins of ERYTHROCYTES.
They are found in all vertebrates and some invertebrates. The
number of globin subunits in the hemoglobin quaternary structure
differs between species. Structures range from monomeric to a
variety of multimeric arrangements

The MeSH Hierarchy
• a

Uses of the MeSH Ontology
• Provide synonyms (“entry terms”)

– E.g., glucose and dextrose
• Provide hypernyms (from the hierarchy)
– E.g., glucose ISA monosaccharide
• Indexing in MEDLINE/PubMED database
– NLM’s bibliographic database:
• 20 million journal articles
• Each article hand-assigned 10-20 MeSH terms

Word Similarity: Thesaurus

Methods
Word Similarity
• Synonymy: a binary relation
– Two words are either synonymous or not
• Similarity (or distance): a looser metric
– Two words are more similar if they share more features of
meaning
• Similarity is properly a relation between senses
– The word “bank” is not similar to the word “slope”
– Bank1 is similar to fund3
– Bank2 is similar to slope5
• But we’ll compute similarity over both words and
senses
Why word similarity
• Information retrieval
• Question answering
• Machine translation
• Natural language generation
• Language modeling
• Automatic essay grading
• Plagiarism detection
• Document clustering
Word similarity and word relatedness
• We often distinguish word similarity from word
relatedness
– Similar words: near-synonyms
– Related words: can be related any way
• car, bicycle: similar
• car, gasoline: related, not similar
• Two classes of similarity algorithms
1) Thesaurus-based algorithms
– Are words “nearby” in hypernym hierarchy?
– Do words have similar glosses (definitions)?
2) Distributional algorithms
– Do words have similar distributional contexts?
Path based similarity
•Intuition: the shorter the path between
two words/senses in a thesaurus hierarchy
graph, the more similar they are.
•Words are quite similar to parents & siblings
•Less similar to words far away in the network.
• Two concepts (senses/synsets) are similar if they are in

the thesaurus hierarchy
• =have a short path between them
• concepts have path 1 to themselves
• 2 to nearest neighbor etc.
Refinements to path-based similarity
• pathlen(c1,c2) = 1 + number of edges in the shortest
path in the hypernym graph between sense nodes c1
and c2
1
• simpath(c1,c2) =
pathlen(c1,c2 )
• Path-length based similarity:

• simpath(c1,c2) = -log pathlen(c1,c2)
• wordsim(w1,w2) = max sim(c1,c2)

c1senses(w1),c2senses(w2)
Example: path-based similarity
simpath(c1,c2) = 1/pathlen(c1,c2)
path-based similarity
simpath(c1,c2) = 1/pathlen(c1,c2)
simpath(nickel,coin) = 1/2 = .5
simpath(fund,budget) = 1/2 = .5
simpath(nickel,currency) = 1/4 = .25
simpath(nickel,money) = 1/6 = .17
simpath(coinage,Richter scale) = 1/6 = .17

Problem with basic path-based similarity
• Assumes each link represents a uniform distance

– But nickel to money seems to us to be closer than nickel to
standard
– Nodes high in the hierarchy are very abstract
• We instead want a metric that

– Represents the cost of each edge independently
– Words connected only through abstract nodes
• are less similar

Information content similarity metrics
Resnik 1995. Using information content to evaluate semantic
similarity in a taxonomy. IJCAI
• Let’s define P(c) as:
– The probability that a randomly selected word in a corpus is
an instance of concept c
– Formally: there is a distinct random variable, ranging over
words, associated with each concept in the hierarchy
• for a given concept, each observed noun is either
– a member of that concept with probability P(c)
– not a member of that concept with probability 1-P(c)
– All words are members of the root node (Entity)
• P(root)=1
– The lower a node in hierarchy, the lower its probability
Information content similarity
• Train by counting in a corpus
– Each instance of hill counts toward frequency
of natural elevation, geological formation, entity, etc
– Let words(c) be the set of all words that are children of node c
• words(“geo-formation”) = {hill,ridge,grotto,coast,cave,shore,natural elevation}
• words(“natural elevation”) = {hill, ridge} entity
å count(w) …
P(c) = wÎwords(c) geological-formation

N
Where words(c) is set of words subsumed by concept c.
N is the #words in corpus and also in thesaurus natural elevation cave shore
IS 7118:NLP Unit-9: Semantics, hill ridge grotto 42coast

Information content similarity
• WordNet hierarchy augmented with probabilities P(c)
D. Lin. 1998. An Information-Theoretic Definition of Similarity. ICML 1998
43
Information content: definitions
• Information content:
IC(c) = -log P(c)
• Most informative subsumer (Lowest common subsumer)
LCS(c1,c2) = The most informative (lowest) node in the hierarchy
subsuming both c1 and c2
•How to use information content IC as

a similarity metric?

Using information content for similarity: the
Resnik method
Philip Resnik. 1995. Using Information Content to Evaluate Semantic Similarity in a Taxonomy. IJCAI
1995.
Philip Resnik. 1999. Semantic Similarity in a Taxonomy: An Information-Based Measure and its Application
to Problems of Ambiguity in Natural Language. JAIR 11, 95-130.
• The similarity between two words is related to their

common information
• The more two words have in common, the more similar
they are
• Resnik: measure common information as:
– The information content of the most informative
(lowest) subsumer (MIS/LCS) of the two nodes
• simresnik(c1,c2) = -log P( LCS(c1,c2) )

Dekang Lin method
Dekang Lin. 1998. An Information-Theoretic Definition of Similarity. ICML
• Intuition: Similarity between A and B is not just what they

have in common
• The more differences between A and B, the less similar
they are:
– Commonality: the more A and B have in common, the more
similar they are
– Difference: the more differences between A and B, the less
similar
• Commonality: IC(common(A,B))
• Difference: IC(description(A,B)-IC(common(A,B))
• Where description(A,B) “describes” A and B IS 7118:NLP Unit-9: Semantics,
46
Dekang Lin similarity theorem
• Similarity Theorem: The similarity between A and B is measured
by the ratio between the amount of information needed to state
the commonality of A and B and the information needed to fully
describe what A and B are
IC(common(A, B))
simLin (A, B) µ
IC(description(A, B))
• The information in common between two concepts is twice the
informationin the lowest common consumer.
• Lin (altering Resnik) defines IC(common(A,B)) as 2 x information of the LCS
2logP(LCS(c1,c2 ))
simLin (c1,c2 ) =
logP(c1 )+ logP(c2 )
47
Lin similarity function
2logP(LCS(c1,c2 ))
simLin (A, B) =
2logP(geological-formation)
simLin (hill,coast) =
logP(hill)+ logP(coast)
2ln0.00176
=
ln0.0000189 + ln0.0000216
=.59 IS 7118:NLP Unit-9: Semantics, 48
Jiang-Cornath Distance
• Related to simLin – expressed as distance instead of
similarity:
• distJC(c1,c2)= 2× log P(LCS(c1,c2))-(log P(c1) + log P(c2))
• Transform into similarity measure by taking the reciprocal:
1
simJC (c1, c 2) =
2  log P(LCS(c1, c2)) - (log P(c1) + log P(c2))

The (extended) Lesk Algorithm

• A thesaurus-based measure that looks at glosses
• Two concepts are similar if their glosses contain similar words
– Drawing paper: paper that is specially prepared for use in drafting
– Decal: the art of transferring designs from specially prepared paper
to a wood or glass or metal surface
• For each n-word phrase that’s in both glosses
• Add a score of n2
• Paper and specially prepared for 1 + 22 = 5
• Compute overlap also for other relations
• glosses of hypernyms and hyponyms, meronyms and other relation of
the two concepts not just in the glosses of the two synsets
• Let RELS be the set of possible wordnet relations with glosses
we compare, then define Extended Lesk measure as:
50
Summary: thesaurus-based similarity
1
sim path (c1,c2 ) =
pathlen(c1,c2 )
2logP(LCS(c1,c2 ))
sim resnik (c1,c2 ) = -logP(LCS(c1,c2 )) sim lin (c1,c2 ) =
1
sim jiangconrath (c1,c2 ) =
logP(c1 )+ logP(c2 )- 2logP(LCS(c1,c2 ))
sim eLesk (c1,c2 ) = å overlap(gloss(r(c1 )),gloss(q(c2 )))
r,qÎRELS

Libraries for computing thesaurus-
based similarity
• NLTK
http://nltk.github.com/api/nltk.corpus.reader.html?highlight=similarity -
nltk.corpus.reader.WordNetCorpusReader.res_similarity
• WordNet::Similarity
http://wn-similarity.sourceforge.net/
– Web-based interface:
http://marimba.d.umn.edu/cgi-bin/similarity/similarity.cgi

Evaluating similarity
• Intrinsic Evaluation:
– Correlation between algorithm and human word similarity
ratings
• Extrinsic (task-based, end-to-end) Evaluation:
– Malapropism (spelling error) detection
– WSD
– Essay grading
– Taking TOEFL multiple-choice vocabulary tests
Levied is closest in meaning to:
imposed, believed, requested, correlated

Word Similarity: Distributional

Similarity(I)
Problems with thesaurus-based meaning
• We don’t have a thesaurus for every language

• Even if we do, they have problems with recall
– Many words are missing
– Most (if not all) phrases are missing
– Some connections between senses are missing
– Thesauri work less well for verbs, adjectives
• Adjectives and verbs have less structured
hyponymy relations

Distributional models of meaning
• Also called vector-space models of meaning
• Offer much higher recall than hand-built thesauri
– Although they tend to have lower precision
• Zellig Harris (1954): “oculist and eye-doctor … occur in
almost the same environments….
If A and B have almost identical environments we say that
they are synonyms.
• Firth (1957): “You shall know a word by the company it

keeps!”
• Intuition: the meaning of a word is related to the distribution of
words around it.
Intuition of distributional word similarity
• Nida example:
A bottle of tesgüino is on the table
Everybody likes tesgüino
Tesgüino makes you drunk
We make tesgüino out of corn.
• From context words humans can guess tesgüino means

– an alcoholic beverage like beer
• Intuition for algorithm:
– Two words are similar if they have similar word contexts.

Reminder: Term-document matrix
• Each cell: count of term t in a document d: tft,d:
– Each document is a count vector in ℕv: a column below
As You Like It Twelfth Night Julius Caesar Henry V

battle 1 1 8 15
soldier 2 2 12 36
fool 37 58 1 5
clown 6 117 0 0

Reminder: Term-document matrix
• Two documents are similar if their vectors are similar

battle 1 1 8 15
soldier 2 2 12 36
fool 37 58 1 5
clown 6 117 0 0

The words in a term-document
matrix
• Each word is a count vector in ℕD: a row below

battle 1 1 8 15
soldier 2 2 12 36
fool 37 58 1 5
clown 6 117 0 0

The words in a term-document
matrix
• Two words are similar if their vectors are similar

battle 1 1 8 15
soldier 2 2 12 36
fool 37 58 1 5
clown 6 117 0 0

The Term-Context matrix
• Instead of using entire documents, use smaller contexts

– Paragraph
– Window of 10 words
• A word is now defined by a vector over counts of
context words

Sample contexts: 20 words (Brown corpus)
• equal amount of sugar, a sliced lemon, a tablespoonful of apricot

preserve or jam, a pinch each of clove and nutmeg,
• on board for their enjoyment. Cautiously she sampled her first
pineapple and another fruit whose taste she likened to that of
• of a recursive type well suited to programming on the digital
computer. In finding the optimal R-stage policy from that of
• substantially affect commerce, for the purpose of gathering
data and information necessary for the study authorized in
the first section of this

Term-context matrix for word similarity
• Two words are similar in meaning if their context
vectors are similar
aardvark computer data pinch result sugar …

apricot 0 0 0 1 0 1
pineapple 0 0 0 1 0 1
digital 0 2 1 0 1 0
information 0 1 6 0 4 0

Should we use raw counts?
• For the term-document matrix
– We used tf-idf instead of raw term counts
• For the term-context matrix

– Positive Pointwise Mutual Information (PPMI) is common

Pointwise Mutual Information
• Pointwise mutual information:
– Do events x and y co-occur more than if they were independent?
PMI(X,Y) = log2 P(x,y)

P(x)P(y)
– PMI between two words: (Church & Hanks 1989)

– Do words x and y co-occur more than if they were independent?
P(word1,word2 )
PMI(word1, word2 ) = log2
P(word1)P(word2 )
– Positive PMI between two words (Niwa & Nitta 1994)
– Replace all PMI values less than 0 with zero

Computing PPMI on a term-context matrix
• Matrix F with W rows (words) and C columns (contexts)
• fij is # of times wi occurs in context cj
C W
fij å fij å fij

pij = W C pi* = j=1 p* j = i=1
W C W C
åå fij åå fij åå fij
i=1 j=1 i=1 j=1 i=1 j=1
pij ìï pmi if pmi > 0

ij ij
pmiij = log2 ppmiij = í
pi* p* j ïî 0 otherwise 67
fij
pij = W C
åå fij
i=1 j=1 C W
p(w=information,c=data) = 6/19 = .32 å fij å fij
p(w=information) = 11/19 = .58
p(wi ) = j=1 p(c j ) = i=1
p(c=data) = 7/19 = .37 N N
p(w,context) p(w)
computer data pinch result sugar
apricot 0.00 0.00 0.05 0.00 0.05 0.11
pineapple 0.00 0.00 0.05 0.00 0.05 0.11
digital 0.11 0.05 0.00 0.05 0.00 0.21
information 0.05 0.32 0.00 0.21 0.00 0.58
68
p(context) 0.16 0.37 0.11 0.26 0.11
p(w,context) p(w)
pij apricot 0.00 0.00 0.05 0.00 0.05 0.11
pmiij = log2 pineapple 0.00 0.00 0.05 0.00 0.05 0.11
pi* p* j
digital 0.11 0.05 0.00 0.05 0.00 0.21
information 0.05 0.32 0.00 0.21 0.00 0.58
p(context) 0.16 0.37 0.11 0.26 0.11
• pmi(information,data) = log2 (.32 / (.37*.58) ) = .57
(.57 using full precision)
PPMI(w,context)
apricot - - 2.25 - 2.25
pineapple - - 2.25 - 2.25
digital 1.66 0.00 - 0.00 -
information 0.00 0.57 - 0.47 - 69
Weighing PMI
• PMI is biased toward infrequent events
• Various weighting schemes help alleviate this
– See Turney and Pantel (2010)
– Add-one smoothing can also help

Add-1 smoothing Prof.R.K.Rao Bandaru

• Add-1 smoothing
apricot 1 1 2 1 2
pineapple 1 1 2 1 2
digital 3 2 1 2 1
information 2 7 1 5 1
p(w,context) [add-1] p(w)

apricot 0.03 0.03 0.05 0.03 0.05 0.18
pineapple 0.03 0.03 0.05 0.03 0.05 0.18
digital 0.08 0.05 0.03 0.05 0.03 0.23
information 0.05 0.18 0.03 0.13 0.03 0.41
p(context) 0.18 0.28 0.15 0.23 0.15 71
PPMI with add-2 smoothing
• Add 2 smoothing Add-2 Smoothed Count(w,context)
apricot 2 2 3 2 3
pineapple 2 2 3 2 3
digital 4 3 2 3 2
information 3 8 2 6 2
p(w,context) [add-2] p(w)
apricot 0.03 0.03 0.05 0.03 0.05 0.20
pineapple 0.03 0.03 0.05 0.03 0.05 0.20
digital 0.07 0.05 0.03 0.05 0.03 0.24
information 0.05 0.14 0.03 0.10 0.03 0.36
p(context) 0.19 0.25 0.17 0.22 0.17 IS 7118:NLP Unit-9: Semantics,
72
Weighted PPMI Prof.R.K.Rao Bandaru
(with add-2 smoothing _

•Regular counts PPMI(w,context)
(Without add-2)
apricot - - 2.25 - 2.25
pineapple - - 2.25 - 2.25
digital 1.66 0.00 - 0.00 -
information 0.00 0.57 - 0.47 -
PPMI(w,context) [add-2]
•With add-2 computer data pinch result sugar
apricot 0.00 0.00 0.56 0.00 0.56
pineapple 0.00 0.00 0.56 0.00 0.56
digital 0.62 0.00 0.00 0.00 0.00
information 0.00 0.58 0.00 0.37 0.00 73
Word Similarity: Distributional

Similarity(II)
Using syntax to define a word’s context
• Zellig Harris (1968)
– “The meaning of entities, and the meaning of grammatical relations among them, is
related to the restriction of combinations of these entities relative to other entities”
• Two words are similar if they have similar parse

contexts
• Duty and responsibility (Chris Callison-Burch’s example)
Modified by additional, administrative, assumed, collective,
adjectives congressional, constitutional …
Objects of assert, assign, assume, attend to, avoid, become,
verbs breach …
It’s not that similar words around them, but

IS 7118:NLP grammatical
Unit-9: Semantics, context can be similar.75
Co-occurrence vectors based on syntactic
dependencies
Dekang Lin, 1998 “Automatic Retrieval and Clustering of Similar Words”
• The contexts C are different dependency relations

– Subject-of- “absorb”
– Prepositional-object of “inside”
• Counts for the word cell:

• The vector is determined by numbers of times
the word occurred in particular
PMI applied to dependency relations
Hindle, Don. 1990. Noun Classification from Predicate-Argument Structure. ACL
Objectof
Object of Count PMI
Count
“drink”
“drink”
ittea 32 11.8
1.3
liquid
anything 32 10.5
5.2
wine
wine 22 9.3
anything
tea 23 5.2
11.8
it
liquid 23 1.3
10.5
• “Drink it” more common than “drink wine”

• But “wine” is a better “drinkable” thing than “it”
Reminder: cosine for computing Sec. 6.3
similarity
Dot product Unit vectors
åi=1 viwi
N
v ·w v w
cos(v, w) = = · =
vw v w
åi=1 vi åi=1 wi
N 2 N 2
vi is the PPMI value for word v in context i

wi is the PPMI value for word w in context i.
Cos(v,w) is the cosine similarity of v and w

Cosine as a similarity metric
• -1: vectors point in opposite
directions
• +1: vectors point in same
directions
• 0: vectors are orthogonal
• Raw frequency or PPMI are non-

negative, so cosine range 0-1

Cosine measure large data computer
apricot 1 0 0
åi=1 viwi
N
v ·w v w digital 0 1 2
cos(v, w) = = · =
vw v w
åi=1 vi åi=1 wi
N 2 N 2 information 1 6 1
Which pair of words is more similar?

1+ 0 + 0 1
cosine(apricot,information) = = =.16
1+0+0 1+36+1 38
cosine(digital,information) = 0+6+2 8
= =.58
0+1+ 4 1+36+1 38 5
cosine(apricot,digital) =
0+0+0
=0
1+0+0 0+1+ 4
Other possible similarity measures
• Out of the four measures given below the Cosine similarity is more popular
measure

End of Semantics
???

IS 7118 Unit-9 Semantics

Uploaded by

Copyright:

Available Formats

IS 7118 Unit-9 Semantics

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

IS 7118 Unit-9 Semantics

Uploaded by

Copyright:

Available Formats

Unit-9: Semantics

IS 7118: Natural Language Processing

IS 7118:NLP Unit-9: Semantics, 2

Word Senses and Word Relations

• A lemma or citation form

• One lemma “bank” can have many meanings:

• Sense (or word sense)

IS 7118:NLP Unit-9: Semantics, 5

– The meaning of a text or discourse

IS 7118:NLP Unit-9: Semantics, 6

IS 7118:NLP Unit-9: Semantics, 8

• Most non-rare words have multiple meanings

• Metonymy or Systematic Polysemy: A systematic relationship

IS 7118:NLP Unit-9: Semantics, 12

• Conversely hypernym/superordinate (“hyper is super”)

Superordinate/hyper vehicle fruit furniture

IS 7118:NLP Unit-9: Semantics, 15

• Troponym: A word that denotes a manner of doing something.

IS 7118:NLP Unit-9: Semantics, 17

WordNet and other Online

IS 7118:NLP Unit-9: Semantics, 20

• A hierarchically organized lexical database

Category Unique Strings

Graph, where nodes

IS 7118:NLP Unit-9: Semantics, 22

IS 7118:NLP Unit-9: Semantics, 23

• The synset (synonym set), the set of near-synonyms,

IS 7118:NLP Unit-9: Semantics, 24

IS 7118:NLP Unit-9: Semantics, 25

IS 7118:NLP Unit-9: Semantics, 26

IS 7118:NLP Unit-9: Semantics, 27

IS 7118:NLP Unit-9: Semantics, 28

IS 7118:NLP Unit-9: Semantics, Prof.R.K.Rao Bandaru

IS 7118:NLP Unit-9: Semantics, 30

IS 7118:NLP Unit-9: Semantics, 31

• Provide synonyms (“entry terms”)

IS 7118:NLP Unit-9: Semantics, 32

Word Similarity: Thesaurus

•Words are quite similar to parents & siblings

•Less similar to words far away in the network.

• Two concepts (senses/synsets) are similar if they are in

• Path-length based similarity:

• wordsim(w1,w2) = max sim(c1,c2)

IS 7118:NLP Unit-9: Semantics, 39

• Assumes each link represents a uniform distance

• We instead want a metric that

IS 7118:NLP Unit-9: Semantics, 40

P(c) = wÎwords(c) geological-formation

IS 7118:NLP Unit-9: Semantics, hill ridge grotto 42coast

•How to use information content IC as

IS 7118:NLP Unit-9: Semantics, 44

• The similarity between two words is related to their

IS 7118:NLP Unit-9: Semantics, 45

• Intuition: Similarity between A and B is not just what they

• Lin (altering Resnik) defines IC(common(A,B)) as 2 x information of the LCS

• Transform into similarity measure by taking the reciprocal:

IS 7118:NLP Unit-9: Semantics, 49

The (extended) Lesk Algorithm

IS 7118:NLP Unit-9: Semantics, 51