1. The CHAOS Project: Theory and Practice
Fabio Massimo Zanzotto
Department of Computer Science, Systems and Production
University of Roma “Tor Vergata”

2. People INVESTIGATORS FORMER CONTRIBUTORS Roberto Basili
Fabio Massimo Zanzotto
Maria Teresa Pazienza
FORMER CONTRIBUTORS
Daniele Pighin
Daniele Previtali
Alessandro Bahgat
Marco Pennacchiotti
Massimo Di Nanni
Michele Vindigni
Luigi Mazzucchelli
Paola Velardi
Paolo Zirilli
Alessandro Cucchiarelli
Alessandro Marziali
Fabrizio Grisoli
Gianluca De Rossi

3. Outline Theory: Customizable parsing architectures
XDG: eXtended Dependency Graph
Task oriented parsing design
Practice: System Implementation and Use
A component-based approach
An object-oriented platform
Linguistic data
Processing modules
How to use the parser in an application
Demo!!!

4. Customizable parsing architectures
Theory
Customizable parsing architectures

5. Motivation The Chaos Project unofficially began in ’96
… on the long tradition of ARIOSTO (Basili, Pazienza, the University of Rome “Tor Vergata” (RTV)
Aim
building robust parsers for Italian and for English
that use verb sub-categorization (syntactic) lexicons induced from corpora
that can be used in applications
Constraints
use the long RTV
“Social” background
Microtheories for microphenomena
Language analysis can be reduced to a cascade of modules (e.g., FSA)
Application-oriented language anaysis (e.g., IE)
Robust (formely, shallow) parsing approaches

6. Motivation contribute-NP-PP(to) value-NP-PP(at) Inf(S1) Inf(S2)
[ Mr. Gaubert ] [contributed] [real estate] [valued] [ at $ 25 million] [to the assets] [of Independent American]

7. Motivation (found on vinyl supports)
Different NLP applications have different performance constraints in term of:
Accuracy
Throughput
Customizable parsing architectures are reusable in different application scenarios if:
the architectural design supports performance control

8. Customizable parsing architectures (found on vinyl supports)
Modularization
clarifies the interdependency between different syntactic information (grammatical/lexicalized)
allows to control
throughput via eliciting modules
quality via a clear relation between modules (prerequisites/contributions)

9. Pi(Si,Ki)=Si+1  Pi(Si)=Si+1
Modular approach
Syntactic parser
SP(S,K)=I  SP(S)=I
Syntactic parsing module:
Pi(Si,Ki)=Si+1  Pi(Si)=Si+1
Modular syntactic parser
SP = Pn... P2P1

10. Modular approach To push a modular approach we need:
a suitable annotation scheme
a classification of the processing modules

11. A suitable annotation scheme
Requirements:
Modularization
a stable representation of partially analyzed structures
Lexicalization
a clear representation of the (semantic) head of a given structure able to activate the lexicalized rule

12. XDG: Extended Dependency Graph
XDG combines constituency and dependency based formalisms
XDGGD=(C,D)
C = {(c,t,h)|cS,t,hc}
D = {(c1,c2,t)| c1,c2C, t}
Nice property: allow to store persistent ambiguity (for interpretations projected by the same nodes)

13. XDG: Extended Dependency Graph
C are constituents
syntactic head
potential semantic governor
D are dependencies among constituents

14. Classification of parsing modules
Pi(XDGi,Ki)=Pi(XDGi)=XDGi+1
The classification is performed according to:
the type of information K used
how they manipulate the sentence representation

15. Task oriented parsing design
Given:
The NLP application requirements R
The test-bed T
A pool of parsing modules PM
The designing activity is:
The research of a combination of the parsing modules PM that fits R on the T

16. NLP application requirements
Target phenomena: es. VP_PP, NP_PP, etc
Metrics:
Recall R per sentence
Precision P per sentence
F-measure per sentence

17. CHAOS: Levels of Analysis
POS
Chunks
Clauses
Dependencies
NPK
VPK
PPK
NNS TO VB IN
PRP MD
Strategies to use with questions you cannot answer

18. Verb dependencies and Clause Boundaries
contribute-NP-PP(to)
value-NP-PP(at)
Inf(S1)
Inf(S2)
[ Mr. Gaubert ] [contributed] [real estate] [valued] [ at $ 25 million] [to the assets] [of Independent American]

19. Verb dependencies and Clause Boundaries
contribute-NP-PP(to)
value-NP-PP(at)
Inf(S1)
Inf(S2)
[ Mr. Gaubert ] [contributed] [real estate] [valued] [ at $ 25 million] [to the assets] [of Independent American]

20. Verb dependencies and Clause Boundaries
contribute-NP-PP(to)
value-NP-PP(at)
Inf(S1)
Inf(S2)
[ Mr. Gaubert ] [contributed] [real estate] [valued] [ at $ 25 million] [to the assets] [of Independent American]

21. Verb dependencies and Clause Boundaries
The algorithm:
Initial Hypoteses:
Minimal boundaries of the clauses in the sentence
Derived Hierarchy
Until all verbs have not been analyzed:
Take the rightmost not analyzed verb v:
Take the lexicalized rules R(v) for the verb v
Find the dependencies of
Augment the clause boundaries

22. System Implementation and Use
Practice
System Implementation and Use

23. A Computational Framework
Object-oriented backbone
Objects for the different data
Objects for the different sub-processes
Linguistic sub-processors as libraries
Coexisting languages: Java, C++, C, Prolog

24. System implementation
A component-based approach
An object-oriented platform
Linguistic data
Textual entities: Text, Paragraphs
XDG
Linguistic processors

25. A Component-based Approach
Advantages:
Computational efficiency
Rapid prototyping
Integration of different technologies
Easy reuse

26. Linguistic processors

27. Linguistic processors
Tokenizer, Complex Tokenizer
Dictionary lookup modules
Yellow page look-up
Morphology analyzer
Name Entity Recognition
Part-of-speech tagging
Chunker
Verb shallow analyzer
Shallow analyzer

28. Linguistic modules Each process is encapsulated in an object
initialize()
Load lexicons and rules (general or domain specific)
finalize()
Dismiss the process rules and lexicons
run()
Enrich the input with the contributes of the process

29. Linguistic processors
Microtheories for microphenomena
Each processor implements its own theory:
It has its language for describing rules
It is written in its own programming language

30. Processor: Yellow page look-up, Morphology analyzer
Dictionary
compra comprare d(a) v.tran.sempl 2.sing.imper.pres ~:u:~
compra comprare d(a) v.tran.sempl 3.sing.ind.pres ~:u:~
comprai comprare d(a) v.tran.sempl 1.sing.ind.pass_rem ~:u:~
comprammo comprare d(a) v.tran.sempl 1.plur.ind.pass_rem ~:u:~
compran comprare d(a) v.tran.sempl 3.plur.ind.pres ~:u:~
comprando comprare d(a) v.tran.sempl geru.pres ~:u:~
comprano comprare d(a) v.tran.sempl 3.plur.ind.pres ~:u:~

31. Processor: Chunker Rules …
constituent_class([_cst1, _cst2, _cst3], 'VerFin', _mor, 1, 3):-
verb_finite(_cst1),
verb_to_have(_cst1),
verb_past_particle(_cst2),
verb_to_be(_cst2),
verb_past_particle(_cst3),
common_morfology(_cst1,_mor).

32. Processor: Verb Shallow Analyser
Sub-categorization lexicon …
pattern(comprare,[
[(oggetto,Post),(per,Post)],
[(oggetto,Post),(da,Post),(per,Post)],
[(oggetto,Post),(a,Post),(per,Post)],[(oggetto,Post)]]).
pattern(comprendere,[[(oggetto,Post)],[],[(oggetto,Post)]]).
pattern(comprimere,[[(oggetto,Post)],[(oggetto,Post)]]).
pattern(compromettere,[[(con,Post)],[(oggetto,Post)]]).
pattern(comunicare,[[],
[(con,Post)],
[(a,Post)],
[(oggetto,Post),(a,Post)],[(oggetto,Post)]]).

33. Implemented Italian Shallow Grammar
Constituent Categories
Part-of-Speech Tags
Chunk Types
Dependency Categories
Dependency Categories over Chunk Types

34. A survival user guide Version stand-alone: Version client-server:
chaosparser -h
Version client-server:
chaosserver –h
chaosclient –h
XDG editor and actual gui:
choasgui

35. Using CHAOS in applications
In JAVA applications:
ConfigurationHandler.initialize();
ConfigurationHandler.parseKBPropFile(“LANGUAGE”,”KB”);
Parser ms = new Parser();
ms.initialize();
In Non-JAVA applications:
Using one of the possible output forms:
XDG in Xml
XDG in Prolog
XDG in QLF (in prolog)

36. Perspective Building a statistical Italian parser
Increasing the Itailan annotated corpora
Reusing existing corpora
TUT
SITAL
VIT

37. Tools
XDG editor
DEMO!!!!
Syntactic annotation transformer

38. People INVESTIGATORS FORMER CONTRIBUTORS Roberto Basili
Fabio Massimo Zanzotto
Maria Teresa Pazienza
FORMER CONTRIBUTORS
Daniele Pighin
Daniele Previtali
Alessandro Bahgat
Marco Pennacchiotti
Massimo Di Nanni
Michele Vindigni
Luigi Mazzucchelli
Paola Velardi
Paolo Zirilli
Alessandro Cucchiarelli
Alessandro Marziali
Fabrizio Grisoli
Gianluca De Rossi