Transcript Resources - CSE, IIT Bombay

CS460/626 : Natural Language
Processing/Speech, NLP and the Web
(Lecture 4– Wordnet and Word Sense
Disambiguation, cntd)
Pushpak Bhattacharyya
CSE Dept.,
IIT Bombay
11th Jan, 2011
Foundation of Wordnet: Lexical
Matrix
Meaning-form relationship
Meanings container
Word forms container
M1
W1
M2
W2
M3
W3
.
.
.
.
.
.
Mk-1
Mk
Wk-1
Wk
Many to many relationship
Meaning-form
Meaning-form
Homonymy
(accidental identity or word borrowing)
Homography
(same picture)
Eg: river bank and
financial bank
Homophony
(same sound)
Eg: write and
right
Polysemy
(shades of
meaning)
Eg: Fall
1. The kingdom
fell
2. The fruit fell
Distributional Similarity



Words which are semantically similar
tend to appear in syntactically similar
contexts.
The neighbors of the words tend to be
the same.
Technically known as Distributional
Similarity.
Synset+Gloss+Example
Crucially needed for concept explication, wordnet building using
another wordnet and wordnet linking.
English Synset: {earthquake, quake, temblor, seism} -- (shaking
and vibration at the surface of the earth resulting from
underground movement along a fault plane of from volcanic
activity)
Hindi Synset: {भूकंप, भूचाल, भूडोल, जलजला, भूकम्प, भू-कंप, भू-कम्प,
ज़लज़ला, भमू िकंप, भमू िकम्प - प्राकृतिक कारणों से पथ्
ृ वी के भीिरी भाग में
कुछ उथल-पुथल होने से ऊपरी भाग के सहसा हहलने की क्रिया
"२००१ में
गुज़राि में आये भूकंप में काफी लोग मारे गये थे"
(shaking of the surface of earth; many were killed in the earthquake in
Gujarat)
Marathi Synset: धरणीकंप,भक
ू ं प - पथ्
ृ वीच्या पोटात द्रव्यक्षोभ होऊन पष्ृ ठभाग
हालण्याची क्रिया "२००१ साली गुजरातिध्ये झालेल्या धरणीकंपात अनेक लोक
ित्ृ युिुखी पडले"
Semantic Relations

Hypernymy and Hyponymy




Relation between word senses (synsets)
X is a hyponym of Y if X is a kind of Y
Hyponymy is transitive and asymmetrical
Hypernymy is inverse of Hyponymy
(lion->animal->animate entity->entity)
Semantic Relations (continued)

Meronymy and Holonymy



Part-whole relation, branch is a part of tree
X is a meronymy of Y if X is a part of Y
Holonymy is the inverse relation of
Meronymy
{kitchen}
………………………. {house}
Lexical Relation

Antonymy



Oppositeness in meaning
Relation between word forms
Often determined by phonetics, word
length etc. ({rise, ascend} vs. {fall,
descend})
WordNet Sub-Graph
Hyponymy
Dwelling,abode
Hypernymy
Meronymy
kitchen
Hyponymy
bckyard
veranda
M
e
r
o
n
y
m
y
bedroom
house,home
Gloss
A place that serves as the living
quarters of one or mor efamilies
Hyponymy
study
guestroom
hermitage
cottage
Troponym and Entailment

Entailment
{snoring – sleeping}

Troponym
{limp, strut – walk}
{whisper – talk}
Entailment
Snoring entails sleeping.
Buying entails paying.

Proper Temporal Inclusion.
Inclusion can be in any way.
Sleeping temporally includes snoring.
Buying temporally includes paying.

Co-extensiveness. (Troponymy)
Limping is a manner of walking.
Opposition among verbs.

{Rise,ascend} {fall,descend}
Tie-untie (do-undo)
Walk-run (slow,fast)
Teach-learn (same activity different perspective)
Rise-fall (motion upward or downward)

Opposition and Entailment.
Hit or miss (entail aim) . Backward presupposition.
Succeed or fail (entail try.)
The causal relationship.
Show- see.
Give- have.
Causation and Entailment.
Giving entails having.
Feeding entails eating.
Kinds of Antonymy
Size
Quality
State
Personality
Direction
Action
Amount
Place
Time
Gender
Small - Big
Good – Bad
Warm – Cool
Dr. Jekyl- Mr. Hyde
East- West
Buy – Sell
Little – A lot
Far – Near
Day - Night
Boy - Girl
Kinds of Meronymy
Component-object Head - Body
Staff-object
Wood - Table
Member-collection Tree - Forest
Feature-Activity
Speech - Conference
Place-Area
Palo Alto - California
Phase-State
Youth - Life
Resource-process
Pen - Writing
Actor-Act
Physician Treatment
Gradation
State
Childhood, Youth, Old
age
Temperature
Hot, Warm, Cold
Action
Sleep, Doze, Wake
Metonymy

Associated with Metaphors which are
epitomes of semantics
Oxford Advanced Learners Dictionary
definition: “The use of a word or phrase
to mean something different from the
literal meaning”

Does it mean Careless Usage?!

Insight from Sanskritic
Tradition

Power of a word


Abhidha, Lakshana, Vyanjana
Meaning of Hall:



The hall is packed (avidha)
The hall burst into laughing (lakshana)
The Hall is full (unsaid: and so we cannot
enter) (vyanjana)
Metaphors in Indian Tradition

upamana and upameya



Former: object being compared
Latter: object being compared with
Puru was like a lion in the battle with
Alexander (Puru: upameya; Lion:
upamana)
Upamana, rupak, atishayokti

upamana: Explicit comparison


rupak: Implicit comparison


Puru was like a lion in the battle with
Alexander
Puru was a lion in the battle with
Alexander
Atishayokti (exaggeration): upamana
and upameya dropped

Puru’s army fled. But the lion fought on.
Modern study (1956 onwards,
Richards et. al.)

Three constituents of metaphor




Vehicle (items used metaphorically)
Tenor (the metaphorical meaning of the former)
Ground (the basis for metaphorical extension)
“The foot of the mountain”



Vehicle: :foot”
Tenor: “lower portion”
Ground: “spatial parallel between the relationship
between the foot to the human body and the
lower portion of the mountain with the rest of the
mountain”
Interaction of semantic fields
(Haas)

Core vs. peripheral semantic fields
Interaction of two words in metonymic
relation brings in new semantic fields
with selective inclusion of features

Leg of a table



Does not stretch or move
Does stand and support
Lakoff’s (1987) contribution



Source Domain
Target Domain
Mapping Relations
Mapping Relations: ontological
correspondences

Anger is heat
of fluid in
container
Heat
(i) Container
(ii) Agitation of
fluid
(iii) Limit of
resistence
(iv) Explosion
Anger
Body
Agitation of
mind
Limit of ability
to suppress
Loss of control
Image Schemas


Categories: Container Contained
Quantity



dramatically; accidents rates were lower
Linear scales and paths: Ram is by far the best
performer
Time



More is up, less is down: Outputs rose
Stationary event: we are coming to exam time
Stationary observer: weeks rush by
Causation: desperation drove her to extreme
steps
Patterns of Metonymy

Container for contained


Possessor for possessed/attribute


Where are you parked? (car)
Represented entity for representative


The kettle boiled (water)
The government will announce new targets
Whole for part

I am going to fill up the car with petrol
Patterns of Metonymy

Part for whole


(contd)
I noticed several new faces in the class
Place for institution

Lalbaug witnessed the largest Ganapati
Question: Can you have part-part metonymy
Purpose of Metonymy

More idiomatic/natural way of expression


Economy


Room 23 is answering (but not *is asleep)
Ease of access to referent


More natural to say the kettle is boiling as
opposed to the water in the kettle is boiling
He is in the phone book (but not *on the back of
my hand)
Highlighting of associated relation

The car in the front decided to turn right (but not
*to smoke a cigarette)
Feature sharing not necessary

In a restaurant:

Jalebii ko abhi dudh chaiye (no feature
sharing)

The elephant now wants some coffee
(feature sharing)
Proverbs

Describes a specific event or state of
affairs which is applicable
metaphorically to a range of events or
states of affairs provided they have the
same or sufficiently similar imageschematic structure
WSD APPROACHES
WSD – Problem Definition

Obtain the sense of



Against a



A set of target words, or of
All words (all word WSD, more difficult)
Sense repository (like the wordnet), or
A thesaurus (not same as wordnet, does
not have semantic relations)
Using the

Context in which the word appears.
Example word: operation




operation ((computer science) data processing in which the result is
completely specified by a rule (especially the processing that results from a
single instruction)) "it can perform millions of operations per second"
operation, military operation (activity by a military or naval force (as a
maneuver or campaign)) "it was a joint operation of the navy and air force"
operation, surgery, surgical operation, surgical procedure, surgical process (a
medical procedure involving an incision with instruments; performed to repair
damage or arrest disease in a living body) "they will schedule the operation as
soon as an operating room is available"; "he died while undergoing surgery"
mathematical process, mathematical operation, operation ((mathematics)
calculation by mathematical methods) "the problems at the end of the chapter
demonstrated the mathematical processes involved in the derivation"; "they
were learning the basic operations of arithmetic"
KNOWLEDEGE BASED v/s MACHINE LEARNING
BASED v/s HYBRID APPROACHES
 Knowledge



Based Approaches
Rely on knowledge resources like WordNet, Thesaurus
etc.
May use grammar rules for disambiguation.
May use hand coded rules for disambiguation.
 Machine
Learning Based Approaches
Rely on corpus evidence.
 Train a model using tagged or untagged corpus.
 Probabilistic/Statistical models.

 Hybrid
Approaches
 Use
corpus evidence as well as semantic relations form
WordNet.
36
SELECTIONAL PREFERENCES
(INDIAN TRADITION)

“Desire” of some words in the sentence (“aakaangksha”).



“Appropriateness” of some other words in the sentence to
fulfil that desire (“yogyataa”).



I saw the boy with long hair.
The verb “saw” and the noun “boy” desire an object here.
I saw the boy with long hair.
The PP “with long hair” can be appropriately connected only to “boy” and
not “saw”.
In case, the ambiguity is still present, “proximity” (“sannidhi”)
can determine the meaning.


E.g. I saw the boy with a telescope.
The PP “with a telescope” can be attached to both “boy” and “saw”, so
ambiguity still present. It is then attached to “boy” using the proximity check.
37
37
SELECTIONAL PREFERENCES
(RECENT LINGUISTIC THEORY)


There are words which demand arguments, like, verbs,
prepositions, adjectives and sometimes nouns. These
arguments are typically nouns.
Arguments must have the property to fulfil the demand. They
must satisfy selectional preferences.

Example
 Give (verb)






agent – animate
obj – direct
obj – indirect
I gave him the book
I gave him the book (yesterday in the school) -> adjunct
How does this help in WSD?

One type of contextual information is the information about the
type of arguments that a word takes.
38
38
WSD USING SELECTIONAL PREFERENCES
AND ARGUMENTS
Sense 1


Sense 2
This airlines serves dinner in
the evening flight.
serve (Verb)
 agent
 object – edible


This airlines serves the sector
between Agra & Delhi.
serve (Verb)
 agent
 object – sector
Requires exhaustive enumeration of:
Argument-structure
Selectional
of verbs.
preferences of arguments.
Description
of properties of words such that meeting the selectional preference
criteria can be decided.
E.g. This flight serves the “region” between Mumbai and Delhi
How do you decide if “region” is compatible with “sector”
39
OVERLAP BASED APPROACHES





Require a Machine Readable Dictionary (MRD).
Find the overlap between the features of different senses of an
ambiguous word (sense bag) and the features of the words in its
context (context bag).
These features could be sense definitions, example sentences,
hypernyms etc.
The features could also be given weights.
The sense which has the maximum overlap is selected as the
contextually appropriate sense.
40
LESK’S ALGORITHM
Sense Bag: contains the words in the definition of a candidate sense of the
ambiguous word.
Context Bag: contains the words in the definition of each sense of each context
word.
E.g. “On burning coal we get ash.”
Ash

Sense 1

Sense 1
Sense 2

Sense 2

Sense 3
Trees of the olive family with pinnate leaves,
thin furrowed bark and gray branches.

The solid residue left when combustible
material is thoroughly burned or oxidized.

Coal
Sense 3
To convert into ash
A piece of glowing carbon or burnt wood.
charcoal.
A black solid combustible substance formed
by the partial decomposition of vegetable
matter without free access to air and under the
influence of moisture and often increased
pressure and temperature that is widely used
as a fuel for burning
41
In this case Sense 2 of ash would be the winner sense.
WALKER’S ALGORITHM

A Thesaurus Based approach.

Step 1: For each sense of the target word find the thesaurus category to

which that sense belongs.
Step 2: Calculate the score for each sense by using the context words. A
context words will add 1 to the score of the sense if the thesaurus category
of the word matches that of the sense.



E.g. The money in this bank fetches an interest of 8% per annum
Target word: bank
Clue words from the context: money, interest, annum, fetch
Sense1: Finance
Sense2: Location
Money
+1
0
Interest
+1
0
Fetch
0
0
Annum
+1
0
Total
3
0
Context words
add 1 to the
sense when
the topic of the
word matches that
of the sense
42