Download Preposition Att problem - Indian Institute of Technology

Survey
yes no Was this document useful for you?
   Thank you for your participation!

* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project

Document related concepts

Spanish grammar wikipedia , lookup

Chinese grammar wikipedia , lookup

Latin syntax wikipedia , lookup

Semantic holism wikipedia , lookup

Esperanto grammar wikipedia , lookup

Polish grammar wikipedia , lookup

Yiddish grammar wikipedia , lookup

Lexical semantics wikipedia , lookup

Symbol grounding problem wikipedia , lookup

Determiner phrase wikipedia , lookup

Pipil grammar wikipedia , lookup

Preposition and postposition wikipedia , lookup

Transcript
Prepositional Phrase Attachment
Problem
03M05601
Ashish Almeida
8 November 2003
PP attachment problem
1
Overview
– Introduction to NLP
– Analysis in UNL system
– Prepositional phrase attachment problem
– Proposed method to handle this problem
8 November 2003
PP attachment problem
2
Motivation
• Analysis involves many complex problems
• Prepositional phrase attachment problem is
one such difficult problem.
• If solved, improve the quality of information
extracted manifold
• No existing system solves the problem
8 November 2003
PP attachment problem
3
Tasks involved in NLP
Analysis and generation
NL understanding
Text
Meaning
NL generation
8 November 2003
PP attachment problem
4
Phases in NLP
• Morphological analysis
• Syntactic analysis
• Semantic analysis
• Discourse integration
• Pragmatic analysis
8 November 2003
PP attachment problem
5
Is NL Compositional ?
• Compsitional expression
– Meaning of the whole from meaning of
parts
e.g.
8 November 2003
strong tea
- rich tea
day by day
- all the time
PP attachment problem
6
Analysis
Morphological + Syntactic + Semantic analysis
• All these phases are dependent on
each other.
• Interactive Vs modular approach
• Analysis in UNL system - interactive
8 November 2003
PP attachment problem
7
UNL …
• UNL is Interlingua
e.g. Ram ate rice with spoon.
@ entry
@ present
eat(icl>do)
agt
obj
John(iof>person)
ins
spoon(icl>artifact)
rice(icl>food)
8 November 2003
PP attachment problem
8
UNL expresion
UNL Expression for Ram ate rice with spoon.
agt(eat(icl>do).@past.@entry, Ram(iof>person))
obj(eat(icl>do).@past.@entry, rice(icl>food))
ins(eat(icl>do).@past.@entry, spoon(icl>tool))
agt(eat(icl>do).@past.@entry, Ram(iof>person))
Relation
8 November 2003
UWs
PP attachment problem
Attributes
9
Analysis in UNL
• Enconverter
–
–
–
–
Natural Language to UNL
Handles one sentence at a time
Predicate preserving parser
Kind of Turing machine
• Components
– Dictionary : lexical units, uw, semantic attributes
– Rule base : head movement rules, relation resolving rules
• Working
– Uses dictionary and rule bases to process the sentence.
8 November 2003
PP attachment problem
10
Prepositional Phrase Attachment Problem
• Type of Structural ambiguity in a sentence
Verb attachment
JohnNP
readVP the reportNP on new technologies.PP
Noun attachment
8 November 2003
PP attachment problem
11
Prepositional Phrase Attachment Problem…
• Noun attachment Vs verb attachment
e.g. John read the report on new technologies.
read
John
*
the report
John
on
read
the report
on
new
technologies
new
technologies
8 November 2003
PP attachment problem
12
Establishing semantic relation
Same structure-different semantic relation
e.g.
1. Ram ate rice with spoon.
……instrument
The UNL for this sentence is
ins(eat(icl>do).@past.@entry, spoon(icl>tool))
2. Ram ate rice with Sita.
……co-agent
The UNL for this sentence is
cag(eat(icl>do).@past.@entry, Sita(iof>person))
8 November 2003
PP attachment problem
13
Difficult problem
• PP attachment problem is simpler or no
problem for human being
- who use world knowledge to process it.
• This world knowledge is not available to
machines.
e.g. travel by night …time
travel by bus …instrument
8 November 2003
PP attachment problem
14
Different sites of attachment
– The search for the policy is going on.
– The test will be held at the end of August.
– In August 1947, India became free from British
rule.
– Wilson received a medal from the commanding
officer at a farewell party.
• There is no restriction on how far the PP can lie from
the word to which it relates.
8 November 2003
PP attachment problem
15
Affinity with preceding phrase
• The preposition of gets attached to a noun phrase or
a verb phrase immediately preceding it.
–
–
–
–
They were involved in the murder of a 90-year-old woman.
It was begun last week by the crew of a giant crane-barge.
He died of an overdose of sleeping pills
The system will be tailored to meet the need of the political
party.
8 November 2003
PP attachment problem
16
Existing methods
• generate mod-obj combination for almost all PP
relations
– E.g He came according to his promise.
agt(come(icl>do)@past.@entry, he)
*mod(come(icl>do)@past.@entry, :01)
obj:01(according to, promise(icl>abstract thing))
mod:01(promise(icl>abstract thing),he)
• Tags introduced manually to resolve phrase
boundaries
– E.g. It delineates <p>the scope of phrases</p> before
<p>conversion of the sentence</p>.
8 November 2003
PP attachment problem
17
Related work
•
•
•
•
Statistical learning methods used
Wordnet is used to find relations between words
Analysis of corpus is required
Not all aspects of problem considered
• The hypothesis does not apply to all cases
“PP attachments obey the principle of locality”
8 November 2003
PP attachment problem
18
Observations
• Prepositions frequency is calculated from British
National Corpus
• Classified into 2 parts
– Simple Preposition
– Ambiguous prepositions
Frequency
Preposition
Poly. count
29391
18214
9343
14
16
of
in
to
by way of
by means of
7
10
8
1
1
8 November 2003
PP attachment problem
19
Addition to Semantic Attributes hierarchy
• Semantic attributes required to disambiguate
• Addition required, if existing attributes fail to classify
• necessary condition
– the attributes should be able to classify the semantically
separate structures as separate entities.
e.g. the train for Delhi
the price for the Hill Road pool
8 November 2003
PP attachment problem
….to()
….mod()
20
Inclusion of preposition in UNL
expression
• a picture on the wall
plc(picture, wall).
• The cat walked across the street.
– Wrong UNL
*plc ( walk, street )
-cat walked along the street
-cat walked across the street
– Correct UNL
plc (walk, :01)
obj:01(across, street)
8 November 2003
PP attachment problem
21
Classification based on syntax structure
• Sentences have different syntactic structure
• Parsing the depends on surface structure
- Active-passive, transitive-di-transitive, present-past participles etc.
• Classification based on syntax pattern
[ Verb + for + Noun phrase]
v-pur
He was waiting for the rainy day.
v-pur
He applied for a certificate.
[ Noun phrase + for + Noun phrase]
n-mod
The search for the policy is going on.
n-mod
He pays the price for his indulgence.
8 November 2003
PP attachment problem
22
Classification based on semantics
• Deciding factors
– Syntax, attributes, preposition, subcategorisation frame(for
verbs)
Partial list of preposition on and its possible semantic relation
Relation
plc
ins
tim
seq
mod
ins
plc
8 November 2003
Example sentence
ON
a picture on a wall
to travel on the bus
He came on Sunday
Report to reception on arrival
a book on South Africa
She played a tune on her guitar
You can get me on 0181 530 3906
PP attachment problem
23
Updating rule base
• Simpler if the classification is perfect.
• Issues involved
– Priority, proper specification
Two rules showing difference in priority – specific to general
Comment
;N/abs for N/abs ;search for policy
delete preposition
for
DL(N,ABS)
{PRE,#FOR:::}
{N,ABS:+PRERES,+FORRES,+pPUR::}P25;
;V FOR N-UNIT-QUARES ;suspend for 2 days
Comment
Delete preposition
for
8 November 2003
DL(VRB){PRE,#FOR:::}
{N,UNIT,TIM,QUARES
:+PRERES,+FORRES,+pDUR::}P30;
PP attachment problem
24
Conclusion
• World knowledge is realized in terms of
semantic attributes.
• Phrasal verbs are not considered
• Idiomatic constructs are not handled
- e.g. day by day
all the time
8 November 2003
PP attachment problem
25