OBJECTIVES

After reading this chapter, the student will be able to understand:

©) Lexical semantics
Attachment for fragment of English
OOO ©

Relations among lexemes and their senses

WordNet
Robust Word Sense Disambiguation (WSD), Dictionary based approach
ee) ee ee

Scanned with CamScanner

 SEMAN TIC i are composed and assigned to nguiss.
§The process whereby MESS KESEn
or ——
(co sTuct Meaning
ince mst
lot,

“Ie meaning of finguistc Mp

:

out u
Seranics involves figure
ia uage to procuce com
lang
mon -sense knowledge abo
TEESE and process world) j
®

t mode ls ofth e
construc
and
the word a eta
antning of leng G uege. General idea of semantic
one ccs isis assocetedtod wh with the mea
uage Sem et ces or utterances and map the
nten
sicis toto take naturel lanq G
aeerpretation
an sema mantic anay
ntic sis is concemed with Creating
analysis
monior some representati ‘ai on OF meenng ning
Cie} ter deals with the me
tus chap
tic inputs this - ics is inapieed by the aes
oui , ons fora = mea
the nng
naarinn Enquis
= ofof Engu isic approach to Semantics within linguistics. Model §
| esemtati
repr
es follo ws:
tics into two parts
of writen text we can civice seman semantics that logicians used for formal logical languages. Logicians focus on logical
mean ing ci incivi ual words (lexical semantics) and words (and, or, not, if, all, some, only, etc.) and do not pay attention to nomiogical
& We

«a The study of
yi ae 4 —
words
r
to give meaning to a sentence (or large (most nouns,verbs and adjectives). The primary advantage of this theory is its ability to
the study of how individual words combine
=
° .
A —_!
— s

explain compositional semantics - how the meaning of a sentence is determined from

s

units}|
=
mbine
ee to combine
i we need them meani of
into meaning
them into the meaning ofits parts. One important aspect of meaning is that it related
Once we have the meaning of the words sentences to
ionality someum the outside world. However, we do not know the world is. A model theoretic @pproach to
the whole sentence the principle-of semantic composit
ed of the meaning of semantics attemptto create a mode!of the worid and determine the truth of a sentance
principle states that the meaning of the whole sentence is compris
of fi
the sentenc e cen be n
compos edA tre
from ¢ sninn wf
the meaningof its using this model. In this theory, the truth of a sentence does not mean that sentence
ts parts thet is the meaning
7

is actually true; it simply means that the sentence is true in the worid being modeled.
constituent words. Netural languegesdo not obeythis principle of compositionality. Often,
a ‘the meaning of the whole is only partially dependent on th = meaning of Its constituents Model theoretic semantics is effective in studying pregmatic as well as semantics.
Le = = = £ + ji £ tnsingdiiale
\Z_y fesin collocates) and sometimes entirely different from the meanings of individuals (e.g., Amongthe source of knowledgetypically used are
in idioms).| e the meaningsof words, .
Hence, this decomposition of semantics may notbe realistic.W/ord meaning is just one e the meanings associated with grammatical structures,
component of semantics.The relationships that exist between words, the domain, the
* knowledge aboutthe structure of the discourse,
word order, the semantic structure, the underiying context and the real-world knowledge,
* Knowledge about the context in which the discourse is occurring, and
ail contribute to the meaning ofa sentencé.Still, compositional and lexical word semantics
remain the dominant approach to semantics in compositional linguistics. There are * Common-sense knowledge about the topic at hand

theories supporting the idea that linguistic knowledge is knowledge about words. This
means that the lexicon containsall the knowledge aboutlanguage. ,

{y_fi Ga)enerec

Scanned with CamScanner

 —_—— a

~ compositional semantics
involves how words combineto for ;

PEE oe
SP
of each word's !
Shee So, * hoowhedge
nani isn't enough for batitahitahe
understood, howis the overall compositional ws“aLephrase asi is meant to be
meaning must havesomething to do with the ibe ila he OES
the phrase. “I don't eat” and “I don't drink’, for example, expressreatdonate
— .
Semantic analysis ES : |e
of the differencein lexical meaning between “ear and “drink.” an een,
Language
generation (or, understanding) way in which the sentenceis constructed . Plays a role as well, as a
demonstra ted beiow. 4.
Ronaldo scored a beautiful
|like you. 2. You like me. Both sentence
S expresstotally different propositions. however
they have tha same words and each word has a clearly understood
goal! meaning. How is #-
——— a5 Syntactic parsing that the meaning has changed?In sentence.1, ‘I”= subject, "you" = object, while in the
NP a —~ (NP nounphrase, * second sentence these are reversed. This means that Overall meaning reles not only
Verb NP ~~ VP verb phrase)
7 | ~ on the meaning of each part, but additionally on syntacihe composition. This premuse is
Det Adjective Noun known as the principle of compositionality. All lanquages contain an infirete number of
f I N
Ronaldo scored a beautiful goal Morphology: score-d word combinations, so memorization of each separate phrasal meaning is mmpessbie.
Figure 1; Understanding Semantics This means that in order to understand the meanings of new phrases, one must rety
on individual word meanings ‘combined with the specific syntachc stucture The roles
Syntax-driven semantic analysis played by lexical and compositional semantics ere equally necessary with regard to
Assigning meaning representations to input based solely on static knowledge from the total understanding of a phrase or sentence. Knowledge of one without the other will
lexicon and the grammar,| _ invariably lead to miscommunication, and an understanding of denotaton, connotation.
and syntactical structure is necessary for compositional understanding of the whole.
1. Lexical semantics ines ee Understanding the difference between these terms and how the ideas they represent
So far, we have focused on the creation of meaning representation of whole sentence. interact is paramountto understanding the meaning of a phrase or sentence.
The approach we took supports the view that words contribute to the meaning of a
sentence but do not themselves have meaning. It is perhaps this view that has led some
an utterance?
to consider the lexicon as a simplelist of words. However,this is narrow concept, too What exactly is meant by “understanding”
a the utteeerance the case of coneneiy
far from reality. Words have meanings; they haveinternal structure, and are involved in * Extracting knowledge about the world from physica! and geometrical
linguis tic inpu
Physical things: ultimately translatng
.: fr ¢
different relationship with other words. All this information can be captured in a systematic
.
structure by lexicon. In this section, we focus on this and other issues related to words. terms... uh huh sage
%
ing how to use! |
More precisely, we focus on lexical semantics, which is concerned with the linguistic means knowing
: "Understanding language is presented with:a
ret

; examination:
ation: the :
studen t
study of systematic, meaning related structure of words or lexemes (the minimal unit and matriculabon
To master a technique. At
ae te

lexicon). It involves meanings of component words then a sked questions about #

Portion of text or speech and
bed ania pois
tye
2
eee ta taa.

erie Bp
ee Pe
“= emt
mates)

>
| : (30) natura Language Processing

Scanned with CamScanner

 =
a

: ofreal )\ : a,
ric definition ransiated by matching SoU rce fragments against a database
“tis difficult to give one gene Way of
sis is probably the best
application of semantic analy’ the corresponding translation fragments, and then recombining —a3
e s Thinking of a concrete
text :
defining the problem
information retrieval
areas of natural language
Semantic analysis vs. other Google solves a Certain part of the problem iin a Statistical way: answers to “trivial kind
processing .
of questions can be located using a web search engine assumes a database (intemet) Be
ds oem
Phonetics: the study of linguistic soun and a clever page ranking system
components‘of words 7
Morphology: the study.of the meaning
e , Domain knowledge driven analysis
scored = score —d = Verb score + past tens expect certain “slots” of information to befilled in football example in the beginning:
employ, employee, employment, .. hearer is aware of missing details and may expect to hear them another example: _
ip een words
Syntax: a study ofthe structural relationsh betw booking a flight restricting to a certain domain allows the useof specific pattems, rules,
Semantics:the study of meaning ” expectations, etc. customer at a restaurant buyingtrain tickets .
discourse
Pragmatics: the study of how language is used to accomplish goals; Applications of semantic analysis
conventions (turn taking, politeness, etc.); relation between language and context-of-
Information extraction : extract small amounts of pertient information from large bodies :
use oO
of text to find an answerto a question for example €4°rdoc seoedy
Semantic analysis often requires syntactic parsing, pragmatics etc. too (in some form; n
not necessarily formallinguistics) Text su mmarization : Information retrieval (cf. Google) and documentclassificatio
Machine translation
JApproaches to semantic analysis for a
for
book plane tickets,query
Human-computer interaction : conversational agents.
Predicate logic restaurant
.
document”
The sentence "a restaurant that serves Chinese food near TUT” corresponds to the >: "please show mehowto widen the margins of my
Expert systems : free help:
meaning representation 3x Restaurant( x) A Serves( x, ChineseFood) A Near( LocationOf(
Surveillance
x), LocationOf( TUT) semantic analysis is equivalentto creating meaning representations
_and
Several well-defined problems unsolved
applicat ions yet
from language.
A few remaining problems
scalability problem (large vocabulary or unrestricted domain) List on the rightiis from Jim Gray s Turing talk: “What next?
in IT"

Statistical approach |
Statistical machine translation (as an example)
find a bilingual database(e.g. parliamentary proceedings in two languages)
learn an alignment: words and phrasesthat correspond to each
other
earn wordorderin
lea i the target , language (probabilities of target word strings)
,

Semantic Analysis
(122) Natural Language Processing

Scanned with CamScanner

 Why is semantic analysis difficult?
Ambiguity of language
A made her duck", for example, could mean
discuss someof the major phrase types an d try to build
| cooked waterfowl for her. phrase structure
| | y
rules to identif
them.
1 created the (plaster?) duck she owns.
Phrase level Constructions
7 caused
; herto quickly lower her head or body.
As discussed earlier, a fundamentalnotion in natural language
waved my magic wand and turned her into undifferentiated waterfowl. is that certain groups of
ease
words behave asconstituents. These constituents are identified group
Commonsense knowledgeis typically omitted from social communications by their ability to occur
example: in similar context. One of the simplest ways to decide whether a group of wordsis a
"Laura hid George's car keys. He wasdrunk.”
phrase, is to seeif it can be substituted with some other group of words without changing
Language understanding often requires unsound inference abduction ((A&
B) and B) € the meaning. If such a substitution is possible in the set of words forms a face. This is
infer A (which is not sound logic) called the substitutiontest. Consider sentence below where we can substitute a number
Language is dynamic:allows defining new terms, allegory, of phrases:
etc.

Whyis semantic analysis important? Henna reads a book.

Power of language: transfer thoughts from a head to Henna reads storybook. ,

another transfer between brains
and a computer as well? ,
Thosegirls read a book.
Language is a very generic representation (the most She read the comic book.
generic?)
* words can describe almost anything We can easily identify the constituents that can be replaced for each other in the
sentences. These are Henna, she, and Those girls and a book, a story book, and a
* ability to reason with language ability to reason about
almost anything (assuming comic book. These are the words that form a phrase. In linguistics, such constituents
the ability to construct a model ofthe world,
too) represent a paradigmatic relationship. Elements that can substitute each otherin certain
2:Attachment for Fragment ofEnglish syntactic positionsaresaid to be membersof oneparadigm. :
Phrase types are namedaftertheir head, which isa lexical ealegoy that determines the
=
SS

Worcs in 2 sentence ere not tied :

f = 4 = ae - as =

properties of the phrase. Thus,if the head is anoun,the phraseIscalled afeun phrase,
if head is a verb.then the phrase is a verb phrase andso onfor other lexical categories
such as adjective and prepositions. Figure below shows the sentences with the noun
Dhrase verb phrase and preposition phrase.
s32-5-

“ENTS to fn form large

Hente tn

= r constituents.
~si4 fe 2
ey
Srees =Ts= and
e . et MS= O80,
Je
The
aed
fo
Wimb ihe rein.i
The roin
oY ledo
Hi. n Court , The
-
beautiful garden
ate
on at
NIG
yin + Wetec4
Poweses het can occur in
-_ =
z — — os 4 ow

the seme Synilecticade conte xt ru

al a ATSIC = LF Ene exem
wos pie,
dd , they
ca
caa
Sipe = tye~ < See
ane 2 oor “Sc omne
OF s et
DS
Hie
ODISC OF i 2 verb
Fae! a ‘ *,.
t - ~

Sueaon nenaae SCP Le Ree ee

Scanned with CamScanner

 ne constituents in parenthesis are opting. This rife a1
ossibly
!
S preceded b _ | Stik States that a noun phrases consists
of a noun, P Y Determiner ang adjective fin th,
all possible NPs) A seel¥® i at order). This rule does
aN pot cover 2" P
. ‘
noun phrase may include bus! modfiers and more than
. 7 a LRA eT Ti

“VP one at adjective. For example, it may include a PreDRs “ional phrase (PP). More than one
rr adjective is handled byallowing an adjecti '
ve phrase (AP) for the adjective in the rule.
after incorporating PP and AP in the phrase structure rule. we ce* the fo!
i
) [|
Qa

Thegirl a 7 NP (Det) (AP) Noun (PP)

i
The following are a few examples of noun phrases
| pe They .--- (1)
the flower | NP i
plucked
The foggy morning we (2)
| Chilled water .... (3)
with along stick
A beautiful lake in Kashmir.... (4)
Figure 2: A sentence with NP. VP. and PP

nyttlehae a Se
Cold banana shake.... (5)
Noun phrase
Let's see how the abovephrases can be generated using phrase structure tues. The (7)
fA noun phrase is a phrase whose head is a noun or a pronoun, optionally accompanied
phrase consists only of a pronoun. The (2) phrase consists of 8 cetermner. an anpect

Bes
by a set of modifiers. It can function as a subject, object or compliment. The modifiers of
(foggy) that stands foran entire adjective phrase. anc a noun The (3} ptrase comanses
a noun phrase can we determine hoursor adjective phrase. The obligatory constituentof
sists ofof 2 determiner
and adjective phrase and noun, (4) phrase comsists (ws an :acecine
Cetermines (he). ‘
a noun phraseis the noun head-all other constituents are optional. These structures can
onai phrase
phrase (beautiful), a noun (lake) and a prepostone ph (in Kashrs} anc (5) atres®
be represented using the phrasestructure rule. As discussed earlier, phrase structure a . suence of nouns. A noun sentenne = fermec 2
rules are of the form A —-BC, which states that constituent A can be rewritten as two
consists of an adjective followed by a sequence oF DOUrS. “ - .
as nominal. None of the phrase structure Tees oscusse
: un, ? discussed =
so fat ae ale hanoe :4
constitutes B and C. These rules specify the element can occur in a phrase and in what ver thes Sftuaton. Ba
nominals.So, we modify our rulesCover
order. Using this notation, we can representthe phrasestructure rules for a noun phrase
as follows. NP — (Det) (AP) Nom (PP)
NP —+ Pronoun Nom — Noun | Noun Nom
bect orSS %
a predicate. The way
i,” — 2 Say lesS
SSL ae
subjej ct. 29 Come
NP — Det Noun Anoun phrase can act as a
NP — Noun demonstrate eachof these uses.
natch. wee
the mea
her disturbed ine
pabey
NP —- Adj Noun The fiOggy damped weat
2hti —— (2)
cold banana5 sh3s |
NP — Det Adj Noun ! Would like
j a nice
ji

caLOM. -.- a
feat [OCA 3)
aytify
. & beau
We can combineall theserule in a single phrase structure rule as follows: Kula botanical gardenIs ai ¥ ; anim Glass
aS subject. In (
n 2) fs
+ aya ae

IN (1), the noun phrase acts

a

NP —- (Det) (Adj) Noun|Pronoun

MP —» (D4) CAP) rent tr Predicate.

NP DOr CAPD NON CPP) Nannioun \Noun (Vern.

Natural Language Processing

Scanned with CamScanner

 Adjective Phrase
Verb Phrase
Analogousto the noun phraseis the verb phrase, which is headed by of verb. Therejg a The head of an adjective phrase (AP)is an aciactivn £2 eee,
2 ape
fairly wide range of reasons that can modify of verb. This makes verb phrase a bit morg may be preceded by an adverb ang hitowed 7
t Complex. The verb phrase organises various elements of the sentence that depends Ashishis love.
; syntactically on the verb find the following are some examples of phrases: The train ts very late,
| Khushbuslept. .... (1) Nb Mysister is fond of animals.
The boy kicked the ball. .... (2) Nb ™? The phrase structure rule for adjective phrase is
Khushbusleptin the garden. .... (3) Net ? AP —- (adv) Adj (PP)
The boygave the girla book. .... (4) Wb MP NP
Adverb Phrase
The Boy gave the girl a book with blue cover. .... (5)N\> NP? NP PP
An adverb phrase consists of an ady

ah

Sy
ate

7
a)
Ub
vt
a

ope
,

3.

‘Tt
1

4
>]
a

1
,

4
2

a
}

@4
oe
we
As you can see from these examples a verb phrase can have a verb {VP —+ Verbin (1)},
is an example.
@ verb followed by an NP {VP — Verb NP in (2)}, a verb followed by a PP {VP —+ Verb
Time passes very quickly.
PP in (3)}, a verb followed by two NPs (VP — Verb NP NP in (4)}, or a verb followed by
two NPs and a PP {VP — Verb NP NP PP in (5)}. In general, the number of NPs in BP is AdvP — (Intens) Adv

limited to two, whereasit is possible to add more than two PPs. Sentences
VP — Verb (NP) (NP) (PP)* Having discussed phraseStructures, sentences A secterce can Neve bearng structure
Things are further complicated by the fact that gbjects mayalso be entire clausesyas in commonly known structures are Ceciaratve structure. mperstwe stuchure yesne
the sentence, / knowthat Taj is one of the seven wonders. Hence, we mustalso allow for question structure and WH question structure
2n alternative phrase statement rule, in with NP is replaced by S. 5 <= yec* Islet rahe tee Taam
Sentences with a declarative structure have 2 Sufnect towet ty = Ore
VP — Verb S predicate of a declarative sentenceis a noun Dorase anc ofeticate G3 ve"> Sees. & B..
Prepositional Phrase ! like horse riding. The phrase structure tule for ceciaraive Sentences are Sem tenonsS
Prepositional phrases are headed by a preposition, They consist of a preposition, possibly S— NP VP
followed by someother constituent, usually a noun phrase, trocture usually
Sentences with an imperative simecture Ususey begin
Sey with the werd ptrase anc lack
: . mac pi cantances 5 ircokcst and s understood ip he “yeu
We played volleyball on the beach. Subject. The subjectof these types of sentences S maid
ca fy commands and $uggesiors, as See we
We can have a preposition phrasethat consists
of just a preposition.
These types of sentences are used SF cymes *
John went outside.
Called imperative. The grammar+ mie
mole for
OF this
SS kind
© of sentence struchre S

The phrase structure rule that captures the S— Vp

above eventualities is as follows.
PP — Prep (NP)

ee OF

(2) Natural Language Procesting

Scanned with CamScanner

 ’

as follows: 3. Relations among iexsrae & their eave a :_

s. nd of sent ences are
‘ . Aexamples ofthi Homonymy, olysemy, Synonymy, Hyponymy_
Look’at the door. |
2 AGive methe book.
~— Stop talking. lexeme can be understood by analysing the relationship of lexemes with otherk jexer
-

.
© Show methelatest design s tions which can be answered ° Lexical semantics information iis usefulfor
wide variety of NLP applications. This
question structure ask que
Sentences with the yes -no ver b, followed by a subject NP. discusses a variety of relationship that holds among lexemes and their senses.
begin with an auxil iary
ences
using yes or no. These sent
examples Homonym _~-
followed by a VP. Here are some
my which is perhaps the simpieat™
The first relationship that we discuss is homony
Do you have a Red pen?
relationship that exists among lexemes. Homonyms are wordsthat have the same form ;
Is awake and cotter? onymy iBaniriver|:
but have different, unrelated meanings. A classic example of hom
bank orfinancial institution). A related idea isthat of homophones that 'refers to words:
Is the game over?
~Can you show me your album? that are pronounced in the same way butdifferent meaning or spelling of both
isg.. be
rule for the expansion of as, as follows: bie
We expand our grammarby adding another and bee, bear and bare ).
“S — Aux NP VP
Polysemy . a
complex. These sentences begin with polysemes |are es
Sentences with WH question structure are more
question may have a WH Many words have more than one meaningof sense. Unlike homonyms,
WHwords (who, which, where, what why and how). A WH §
phenomenon is called polysemy or lexical a
the following WH questions: words with related meanings. This linguistic
Consider
phraseas a subject or mayinclu de another subject. ambiguous andcalled polysemous. For oo
ambiguity. Words that have several senses are as
Which team won the match? of furniture, a person, the act of presiding
example, the word “chair” can refer to a piece
a WH word. How oy"Is a-poly semy asiits two meaning- to hire —
This sentence is similar to a declarative sentence except it contains over a discussion etc. The word “
empl
use, only -
simple rule to handle this typeof sentencestructureis y2an idea)are related. In a particular
(employ a person) and to accept (emplo
S — Wh-NP VP one of these meanings is correct. .
Another type of WH questions structure is one that involves more than one NP.In this
Hyponymy ~~ ree
hypemym ohiae
type of questions, the auxiliary verb comes before the subject NP, just as in yes-no generalsense. The word automobileisa
The hypernymiisa word with the more . In the
questions structure. is a wordw ithth e most specific meaning
for a car and a truck. The hyponym
is a hyponymof automobile.Antonymis;
Which cameras can you show mein your shop?
relationship between car and automobile, car : The ce
ings.
ess opposite mean
Therule for this type of WH questionsis holds betwee n words that expr og
a semantic relationship that nym of Blac k.
is an anto
of Bad, and Wh ite
word Good is an antonym
e S$ —> Wh-NP Aux NP VP

SemanticAnalysis

Scanned with CamScanner

 . ie
Relations
~~ The word synonym defines the relationship betweendifferent words that have a simi, The mostfrequently encoded relation among
synsets is the wade B x:
2 a meaning. A simple way to decide whether two words are synonymous is to check for Me) z
links more ¢
i substitutability. Two words are synonyms in a context if they
can be substituted for each (also called hyperonymy, hyponymyorISArelation). It
specific ones fike said
(furniture, piece_of_furniture} to increasingly
other without changing the meaning of the sentence. Thus, WordNetstates that the category furniture include
s bed, which in om
‘These relationships are usefulin organising wordsin lexical databases one widely known ely, concept slike bed and bunkbe d make up the estegon ‘en
bunkbed; convers
is t
root node {entity}. Hyponymy relation
noun hierarchies ultimately go up the
lexical database is WordNet discussed in next topic.
DT 2&ined Q Coy
> Print . if an armchair is a kindof chair, and if a chair is a kind offurniture,then anarmch
Ji WordNet| —— and vee
= ———— TS EO kind of furniture. WordNet distinguishes among Types (common nouns}
WordNet is a large lexical database of English. Nouns, verbs, adjectives and adverbs are (specific persons, countries and geographic entities). Thus, armchair is a type of chair,
grouped into sets of cognitive synonyms (synsets), each expressing a distinct concept. Barack Obama is an instance of a president. Instances are always leaf (terminal) nodes
Synsets are interlinked by means of conceptual-semantic and lexical relations. The in their hierarchies.
resulting network of meaningfully related words and concepts can be navigated with the
(~ Meronymy, the part-whole relation holds between synsets fke {char} and (back, i:
browser. WordNetis also freely and publicly available for download. WordNet's structure
- backrest}, {seat} and {leg}:)Parts are inherited from their super ordinates: f a chairhas
makes it a useful tool for computational linguistics and natural language
processing, legs, then an armchair has legs as well. Parts ere not inhented “upward” as they may be “
vie
WordNet superficially resembles a thesaurus, in that it groups words together
based on characteristic only of specific kinds of things rather than the class as a whole: chars and
: oo
their meanings. However, there are some important distinctions.
First, WordNet interlinks kinds of chairs havelegs, but notall kinds of furniture have legs.
of the :
Verb synsets are arranged into hierarchies 2s well, verbs towards the bottom
not just word forms—strings of letters—but specific
senses of words. As a result,
words that are found in close proximity to one anotherin the network express increasingly specific manners Characterang an event, 2s _ se
are semantically trees (troponyms)
disambiguated. Second, WordNet labels the semantic relations among expressed depencs on the je :
words, whereas in {communicate}-{talk}-{whisper}. The specific manner
the groupings of words in a thesaurus doesnotfollow any explicit pattern oth er than just one dimension along which: =
semantic field; volume (as in the example above) is
meaning similarity. or intensity of emabon {iike- - et
verbs can be elaborated. Others are speed (move-jog-run)
g events that necessari ly and unidirectionaly ented one -
Structure love-idolize). Verbs describin
anotherare linked: {buy}{pay}. {succeed}-{try}. {show}-{see}, etc. eee
The main relation arnong words in WordNet is synonymy, as between the words shut
hike watery ad
Adjectives are organized in terms of antonymy. Pairs of “direct” antonyms
and close or car and automobile. Synonyms--words that denote the same c o nt: d members. Each of these polar
are interchangeable in many contexts--are groupedinto unordereg sets volelEat and young-old reflect the strong semantic contractof their
(synsets). Each ary is _— to" :
of WordNet’s 117 000 synsets is linked to other synsets by means ofas adjectives in turn is linked to a number of “semantically similar” ones:
wet to soggy, waterlogged , etc. Senantcal yay ics
of “conceptual relations.” Additionally, a synset contains
a brief definition a vend parched, arid, dessicated and bone-cdry and
) and, the contral member of the OSS pole. —
in most cases, one or more short sentencesillustrating the useofthe syns alos similar adjectives are “indirect antonyms” of
as many distincyrecte, Relation al adjectives (‘pertainyms*) point to the nouns they are derived from coin
Word forms with several distinct meanings are represented jn
Thus, each form-rmeaning pair in WordNet is unique. crime).

Natural Language Processing

Scanned with CamScanner

 atl wee wee

ly, mostl y, reall y, etc.) as ie majority of “4

| 4(hard movefastorto direct and manage). But this does not create :3
: —

eThereare only few adverbs in WordNet * djectives via morphological affixation

d from a give any thought to understanding that what constitutes the concen =
i English adverbsare straightforwardly derive
~~(surprisingly, strangely, etc.) . or phrase, but we generally arrive at the correct one. The " is afcen
ee: Applications of WordNet people are good aresolving ambiguity by considering the context of the y
or coconutprincess. Except for jokes and puns, whereit is intended, are
. “WordNet has found numerousapplications in problemsrelate d with IR and NLP. Some
of these are given below: perceived as such. However, ambiguities existing at different levels are one ofthe 1
challenges in computationallinguistics. Re
: ~ ConceptIdentification in Natural Language: WordNet can be usedto identify concepts
pertaining to a term,to suit them to the full semantic richness and complexity of a given Letus try to understand why ambiguity is difficult. This is becausetrrresees the;
information need. possible interpretations of natural language. Suppose each word nar Suit te cad ;
.
Word Sense Disambiguation: WordNet combines features of a number of the other
is ambiguousandhasthreepossible interpretations. The tata: TLImier of interpretations.
resources commonly used in disambiguation work. It offers sense definitions of words,
of the whole sentenceis 3° = 3561. Further, synthetic and pragmatic ambiguities make:
a in
the actual numberofinterpretations even larger. Resolving a these i
identifies synsets of synonyms, defines a number of semantics relations and is freely
available. This makesit the (currently) best known and mostutilized resource for word — a reasonable amountoftimeis difficult. There are words with a much larger number of _ =i
sense disambiguation. sensors that then considered in this example. This gives a clear picture of the difficulty =

Automatic Query Expansion: WordNet semantic relations can be involved in the automatic interpretation of natural languages. si a
used to expand
queries so that the search for a documentis not confined to the Ambiguity is the property oflinguistic expressions. Ambiguity means capable of being ~
pattern-matching of
query terms, but also covers synonyms. understood in more. than one way of having more than one- meaning. It refers to a 4
Document Summarization: WordNethas found useful situation where an expression can have more thanonepartition. Ambiguity can occur at a: :
application in text summarization.
Few approachesutilize information from WordNet four different levels: ; %
to computelexical chains.
~ Lexical
5. Robust Word Sense Disambiguation (WSD
)-
Dictionary based approach to its internal structure or to its syntactic class. For example in the sentence, look at the
_. aoe
Mostofusfind it difficult to understand screen, look is verb where as in she gave me a stem look,itis a noun. However this type sy
by computers are not able to under
stand language
the way people are. This is because
we do not realise how weight and ambig
of ambiguity is viewed as part of speech tagging in NLP andis considered to have been oe
uous natural
languagesare. Ambiguity that is Solved with reasonable accuracy.
having more than one meaning,
can be result of syntax.
Or semantics. Vaguenessis not
the same as amb iguity. In vague
have only one meaning but theyla
ness, words or phrases _
ckclarity, which makes it diffic
meaning. ult to arrive at a precise
.
In many cases, a single
. word in a | anguage corr
ta esponds to more than
a
= for example the noun Bank one thought,
(financia | institution of
bank of a river) and the ver
b run (to

~(44) natura Language Processing

Scanned with CamScanner

 =
= erry gis aes.
St eher ar heen an thal :

we understand that words have different

re eo: ways in which sequence of words can be grammatically structureg meanings based
on the contdi j sa
the sentence.If we talk about human
languages, then they are ambiguoustoo
aa ayers ere c . son. For example, the man Sawthe g gig many words canbe interpreted in
Eachhie stuctunng jeads to a diferent interpretation. ro muttiple ways depending upon the context 5
ee asks “qt is undiear & ambiguous whether the Man saw a girl Carrying a occurrence.
meaning ofthe
telescope. It is the syntax, not the Word sense disambiguationin natural language processing (NLP), noytedatos oar
telescope, or he saw her through the
on whether the preposition “with” js ability to determine which meaning of word is activated by the wee ofwcedede3 paicanecy
3 “word which is unclear. The meaning is dependent =
"attached to the girl or the man. context. Lexical ambiguity, syntactic o¢ semantic, is one of the very first problemsthat
any NLP system faces. Part-of-speech (POS) taggers with high ievel of acouracy can
Semantic —
themselves can be solve Word's syntactic ambiguity. On the other hand. the problem of resolving semantic
Semantic ambiguity occurs when the meaning of the word
misinterpreted. For example, the meaning of words in the phrase can be combinedin ambiguity is called WSD (word sense Cisambiguation). Resohing semantic ambiguityis
harder than resolving syntactic ambiguity.
different ways, leading to different interpretations.
For example, consider the two examples of the distinct sense that exist for the anil
Iraqi head seeks arms
“bank”-
The homograph “head” can be interpreted as a noun meaning either chief cr anatomical
The bank will not be accepting cash on Saturdays.
head of a body. Likewise the homograph arms can be interpreted as a plural noun
mesning ether weapons or bocyparts.
The river overflowed the bank.
The occurrence of the word bank clearly denotes the Gistnct meanmg. In the frst
Pragmatic
sentence,it means commercial (finance) banks, while in the second sentence: frefers
Pragmatic ambiguity refers to a situation where the context of a phrase gives it multiple
to the river bank. Hence,if it would be disambiguated by WSD then the correct meaning)
interpretations.
to the above sentencescan be assigned as follows —
For example, Give it to the kids. Here “it” may refer to many things depending on the
- The bank/financialinstitution will not be accepting cash on Saturdays. -
context. Consider a larger context.
The river overflowed the bank/riverfront.
Cakeis on the table. | have prepared some snacks. Giveit to kids.
The evaluation of WSD requires the following two inputs: as
It is not clear whetherit refers to cakeor snacksfor both. Perhaps a larger context
help us.
may
A Dictionary: The very first input for evaluation of WSD is dichonary, which is used to =
specify the senses to be disambiguated. Si
Cakeis on the table. | have prepared somestacks. Give it
to kids. Kids enjoyed cake
and snacks Test Corpus: Anotherinput required by WSD is the high-annotated test corpus thathas
Now it is clear that it refers to both snacks
the target or correct-senses. The test corpora can be of two types: =e
Lexical sample - This kind of corpora is used in the system, where Ris required to |
and the cake. Resolving these type of
ambiguous required Discourse Processing *
disambiguate a small sample of words. 2 3a
© All-words- This kind of corpora is used in the system, where @ 58 expected to sae
disambiguateall the wordsin a piece of running text 7
4

_ Natural Language Processing

Scanned with CamScanner

 = a Rie TaE SE
enSOe -
aoe = 2
oy ; Mi ae te e
: ' Rat eee eee a

| "Dictionary-based or Knowledge-based Approach ws D) 1 Pay eh os =

‘Asthe name suggests,for disambiguation, these methods primarily rely on dictionateg cone:
Solid body which
faites {0 a point
treasures and lexical knowledge base. They do not use corpora evidencg ie
~ disambiguation. The Lesk methodis the seminal dictionary-based method introducead . something of this shape whether
Solid or hollow
2 byMichael Lesk in 1986. The Lesk definition, on which the Lesk algorithm is based, jg Fruit of certain evergreen trees
“measure overlap between sensedefinitions for all words in context”. Howe As can be seen,
in 2000, Kilgarriff and Rosensweig gave the simplified Lesk definition as ‘‘Measure pine#1 ¢ Cone#1 = 0
overlap between sense definitions of word and current context”, which furthe, pine#2 G Cone#1 =0
meansidentify the correct sense for one word ata time. Here the current contextjis the pine#1 G Cone#2 = 1
set of words in the surrounding sentence or paragraph.
pine#2 ¢ Cone#2= 0
The Leskalgorithm is based on the assumption that words in a given “neighbourhoog: Pine#1 © Cone#3 = 2°
(section of text) will tend to share a commontopic. A simplified version of the Lesk
Pine#2 ¢ Cone#3 = 0
algorithm is to compare the dictionary definition of an ambiguous wordwith the terms
contained in its neighbourhood. the best intersection is Pine #1 C Cone #3 = 2.

Versions have been adapted to use WordNet. An implementation might look like this: -
1. for every sense of the word being disambiguated one should count the amountof
wordsthat are in both neighbourhoodof that word and in the dictionary definition of
that sense ,
2. the sense that is to be chosen is the sense which has the biggest number ofthis
count

A frequently used example illustrating this algorithm is for the context “pine cone”. The
following dictionary definitions are used:
Pine:
e Kinds of evergreen tree with needle-shapedleaves
¢ Waste away through sorroworillness

Scanned with CamScanner

 al
Expected ¢Questions _
¥. What is semantic analysis? why otfiartic analysis difficult? ExplainVat
: |
is.
approachesto semantic analys
fol low ing rel ati ons hip s between word meanings.
Explain with suitab le exampl es
my
yse my, Syn ony my, Ant ony my, Hypernomy, Hyponomy, Merono
Homonymy, Pol
between he
s different semantic relationships
What:is semantic analysis? Discus
‘words.
dNet? Explain with example.
What is WordNet? HowIs “sense” defi ned in Wor
discuss dictionary }
_ What do you mean by word sense disambiguation (WSD)?
based approach for WSD.
Discuss knowledge
What do you mean by word sense disambiguation (WSD)?
based WSD
discuss machine
What do you mean by word sense disambiguation (WSD)?
learning based( Navie based) approach for WSD.
ied for word sense
Explain how a supervised learning algorithm can be appl
disambiguation:

4 ye

Bes 5 Natural Language Processing

Scanned with CamScanner