REGNET

1
REGNET
An E-Government Infrastructure for Regulation
Parsing and Relatedness Analysis
Gloria Lau, Dr. Shawn Kerrigan, Prof. Kincho Law,
Prof. Gio Wiederhold http//eig.stanford.edu/regne
t Contact glau_at_stanford.edu http//eig.stanford
.edu/glau
2
Motivation

• Multiple sources of regulations
• Multiple jurisdictions federal, state, local,
  etc.
• Different formats, terminologies, contexts

• Amending rules, conflicting ideas

3
Motivation

• Multiple sources of regulations
• Multiple jurisdictions federal, state, local,
  etc.
• Different formats, terminologies, contexts
• Amending rules, conflicting ideas
• ? Need for a repository
• Locate relevant information
• E.g., small business penalty fees for violations
• ? Need for analysis tool
• Complexity of regulations
• Multiple jurisdictions
• Understanding of regulations their
  relationships

4
Example 1 Related Provisions

• ADAAG Appendix 4.6.3
• Such a curb ramp opening must be located
  within the access aisle boundaries, not within
  the parking space boundaries.
• CBC 1129B.4.3
• Ramps shall not encroach into any parking
  space.
• Exception 1. Ramps located at the front of
  accessible parking spaces may encroach into the
  length of such spaces
• CBC allows curb ramps encroaching into accessible
  parking stall access aisles, while ADA disallows
  encroachment into any portion of the stall.

5
Example 2 Related but Conflicting Provisions

• ADAAG 4.7.2
• Slope. Transitions from ramps to walks,
  gutters, or streets shall be flush and free of
  abrupt changes
• CBC 1127B.5.5
• Beveled lip. The lower end of each curb ramp
  shall have a ½ inch (13mm) lip beveled at 45
  degrees as a detectable way-finding edge for
  persons with visual impairments.
• ADAAG focuses on wheelchair traversal CBC
  focuses on the visually impaired when using a
  cane.

6
Scope

• 1. Overview
• Examples of system capabilities
• 2. Repository development 3. Relatedness
  analysis

7
Overview of System Capabilities Parsing
40CFR natural structure
Original 40CFR
8
Overview of System Capabilities Parsing
IBC in 2-columned PDF
XML hierarchy

• ltregulation id"ibc" name"international building
  code" type"private"gt
• ltregElement id"ibc.1107" name"special
  occupancies"gt
• ltregElement id"ibc.1107.2" nameassembly
  area seating"gt
• ltreference id"ibc.1107.2.4.1" times"1" /gt
  
• ltconcept name"assembl area" times"1" /gt
• ltregTextgtAssembly areas with fixed seating
  shall comply with Sections lt/regTextgt
• ltregElement id"ibc.1107.2.1"
  name"services"gt ... lt/regElementgt
• lt/regElementgt
• lt/regElementgt
• lt/regulationgt

9
Overview of System Capabilities Feature Parsing
Usages of features
Extracted features
10
Overview of System Capabilities Comparisons
Regulation comparison 40CFR vs. 22CCR
11
Overview of System Capabilities E-rulemaking
Drafted regulations compared with public comments
12
Scope

• 1. Overview
• Examples of system capabilities
• 2. Repository development 3. Relatedness
  analysis

13
Repository development
14
Shallow parser

• Data Source
• Americans with Disabilities Act Accessibility
  Guide (ADAAG), Uniform Federal Accessibility
  Standards (UFAS), Code of Federal Regulations
  Title 40 (40CFR), UK and Scottish Disability
  Discrimination Act, etc.
• Current standard HTML, PDF, hardcopy...
• Our system standard XML
• Unit of extraction section/provision
• ltregElement idufas.4.32.1 nameminimum
  number asterisk0 gt
• ltregTextgt Fixed or built-in seating, ...
  lt/regTextgt
• ltref nameufas.4.5 num1 /gt
• ltref nameufas.4.32 num1 /gt
• lt/regElementgt

15
Shallow parser PDF ? Basic XML format
16
Shallow parser HTML ? Basic XML format
ltregulation id"40.cfr" name"code of federal
regulations" type"federal"gt ... ltregElement
id"40.cfr.279.12.c" name"Burning in particular
units."gt ... ltregElement id"40.cfr.279.12.c.3
" name""gt ltreference id"40.cfr.264.O"
times"1" /gt ... ltconcept name"waste
incinerator" times"1" /gt ltregTextgt
Hazardous waste incinerators subject to
regulation under subpart O of parts 264 or 265 of
this chapter. lt/regTextgt lt/regElementgt
lt/regElementgt lt/regulationgt
17
Shallow parser extracting references

• ltregulation id"40.cfr" name"code of federal
  regulations" type"federal"gt ...
• ltregElement id"40.cfr.279.12.c" name"Burning
  in particular units"gt ...
• ltregElement id"40.cfr.279.12.c.3" name""gt
• ltreference id"40.cfr.264.O" times"1" /gt
  ...
• ltconcept name"waste incinerator" times"1"
  /gt
• ltregTextgt Hazardous waste incinerators
  subject to regulation under subpart O of parts
  264 or 265 of this chapter. lt/regTextgt
• lt/regElementgt
• lt/regElementgt
• lt/regulationgt

18
Shallow parser feature extraction

• Non-structural characteristics specific to a
  corpus
• To aid user retrieval of relevant materials
• For analysis purpose

19
Shallow parser feature extraction

• Generic features
• Concepts - noun phrases
• Exceptions - negated provisions
• Definitions - terminologies defined in
  regulations
• Domain-specific features
• Glossary terms - definitions from reference
  guides

• Author-prescribed indices - concepts from field
  handbooks
• Measurements - e.g., 2 inches max, 4 ppm
• Chemicals - list of drinking water contaminants
  from EPA
• Effective dates - provision updates

20
Example of definition/glossary tags

• Original section 3.5 from the ADAAG
• 3.5 DEFINITIONS.
• Accessible. Describes a site, building,
  facility, or portion thereof
• Clear. Unobstructed.
• Refined section 3.5 in XML format
• ltregElement nameadaag.3.5 titledefinitions
  asterisk0gt
• ltindexTerm namefacility num1 /gt
• ltdefinitiongt
• lttermgt accessible lt/termgt
• ltdefinedAsgt Describes a site, building,
  facility, or portion thereof... lt/definedAsgt
• lt/definitiongt
• ltdefinitiongt
• lttermgt clear lt/termgt
• ltdefinedAsgt Unobstructed. lt/definedAsgt
• lt/definitiongt
• lt/regElementgt

21
Example of indexTerm, concept, measurement
exception tags

• Original section 4.6.3 from the UFAS
• 4.6.3 PARKING SPACES. Parking spaces for
  disabled people shall be at least 96 in (2440 mm)
  wide and shall have an adjacent access aisle 60
  in (1525 mm) wide minimum (see Fig. 9). Parking
  access aisles shall be part of ...
• EXCEPTION an adjacent access aisle at least
  96 in (2440 mm) wide complying with 4.5...
• Refined section 4.6.3 in XML format
• ltregElement nameufas.4.6.3 titleparking
  spaces asterisk1gt
• ltconcept nameaccess aisle num3 /gt
• ltindexTerm nameaccessible circulation
  route num1 /gt
• ltmeasurement unitinch magnitude96
  quantifiermin /gt
• ltref nameufas.4.5 num1 /gt
• ltregTextgt Parking spaces for disabled
  people shall ... lt/regTextgt
• ltexceptiongt If accessible parking spaces
  for ... lt/exceptiongt
• lt/regElementgt

22
Usages of extracted features revisited
Usages of features
Extracted features
23
Scope

• 1. Overview
• Examples of system capabilities
• 2. Repository development 3. Relatedness
  analysis

24
Relatedness analysis
25
Relatedness analysis

• To utilize the structure, referencing of
  regulations and domain knowledge to obtain a
  better comparison
• Measure
• Similarity score f(A, U) ? (0, 1)
• Nodes A and U are provisions from two different
  regulation trees

f ? (0, 1)
26
Base score f0 computation

• Linear combination of feature matching
• F(A,U,i) similarity score between Sections
  (A,U) based on feature i
• N total number of features

• Feature matching
• Based on the Vector model using cosine similarity
  as the distance between feature vectors
• Similarity between two documents M and N
• dM and dN are document vectors
• Cosine is normalized gt always between 0 and 1

27
Example of feature vectors

• Traditional term match
• each index term i is assigned a positive and
  non-binary weight wi,M in each document vector d
  M
• Weight selection
• Frequency of term, or
• tf ? idf model
• tf term frequency term density
• idf inverse document frequency log(n/ni)
  term rarity
• Excluding stopwords
• Feature concept
• Concept vectors are formed per provision based on
  concept frequency in each provision
• F(provision 1, provision 2, featureconcept)
• cosine between two concept vectors

28
Axis dependency non-Boolean matching

• Vector model assumes mutual independence between
  axes
• Domain experts do not necessarily agree
• A measurement of 2 inches max can be a 70
  match to 2 inches
• Synonyms exist, e.g., ontology defined for
  chemicals
• Limitation observed
• Need flexibility to model domain knowledge, such
  as a 0, 50, 75 and 100 measurement match

29
Proposed non-Boolean matching model

• Define a feature matching matrix E
• Eij match between features i and j
• E.g., a 3-dimensional vector space using 2 ppm,
  2 ppm max and 2 ft as the first, second and
  third measurement axes
• E
• Vector space transformation
• Map feature vectors onto an alternate space via
  matrix D
• Cosines are computed on the consolidated
  frequency vectors
• E.g., similarity based on measurements

30
Vector space transformation

• Define D such that E DTD is fulfilled
• Cosine between the consolidated frequency
  vectors
• Reduces to a Boolean cosine when E I

31
Score refinements based on regulation structure

• Neighbor inclusion
• Diffusion of similarity between clusters of nodes
  in the tree
• Self vs. parent-sibling-child (psc), fs-psc
• psc vs. psc, fpsc-psc

32
Neighbor inclusion psc vs. psc

• Take a linear combination of neighboring pair
  scores
• Formulate a neighbor structure matrix N
• Define score matrix ?
• We have ?psc-psc NA?0NUT

33
Neighbor inclusion self vs. psc

• Take a linear combination of neighbor vs. self
  scores
• Formulate a neighbor structure matrix N
• Define score matrix ?
• We have ?s-psc ½ (?0NUT NA?0)

34
Score refinements based on regulation structure

• Reference distribution
• Diffusion of similarity between referencing nodes
  and referenced nodes in the tree
• E.g., f(A5.3, U6.4(a)) updates f(A2.1, U3.3)

35
Reference distribution s-ref and ref-ref

• Take a linear combination of reference vs. self
  and reference vs. reference scores
• Formulate a reference structure matrix R
• Define score matrix ?
• We have ?ref-ref RA?0RUT and ?s-ref ½ (?0RUT
  RA?0)

36
Example of results UFAS vs BS8300

• Phrasing difference between American and British
  regulations
• ufas.4.13.9 Door Hardware. Handles, pulls,
  latches, locks, and other operating devices on
  accessible doors shall have a shape that is easy
  
• bs8300.12.5.4.2 Door Furniture. Door handles on
  hinged and sliding doors in accessible bedrooms
  should be easy to grip
• Neighbor similarities imply similarity between
  the interested nodes

37
Example of results almost identical provisions
Regulation comparison 40CFR vs. CCR
38
Example of results e-rulemaking

• Application domain e-rulemaking
• Comparison between draft of rules and the
  associated public comments
• ADAAG Chapter 11, rights-of-way draft
• Less than 15 pages
• Over 1400 public comments received within 4
  months
• Comments 10MB in size most are several pages
  long
• ? New regulation draft can easily generate a huge
  amount of data that needs to be reviewed and
  analyzed

39
Example of results e-rulemaking
Regulations compared with public comments
40
Example of results e-rulemaking

• Related draft section and public comment
• Adaag.1105.4.1
• Where signal timing is inadequate for full
  crossing of all traffic lanes or where the
  crossing is not signalized, cut-through medians
• Deborah Wood, October 29, 2002
• This often means walk lights that are so short
  in duration that by the time a person who is
  blind realizes
• No identified related section
• Donna Ring, September 6, 2002
• If you become blind, no amount of electronics
  will make you safe You have to learn modern
  blindness skills from a good teacher. You have
  to practice your new skills
• ? Concern not addressed in the draft

41
Conclusions

• An infrastructure for
• Repository for regulations
• Shallow parser
• Feature extractions
• Similarity comparison
• Base score
• Score refinements
• Results
• Comparisons between Federal codes, European codes
• Application to e-rulemaking
• Future Directions
• Extension of application to other domains of
  semi-structured documents
• Conflict analysis?

42
Thank You!