L-ISA Learning Domain Specific ISA relations from the WEB

1
L-ISALearning Domain Specific ISA relations
from the WEB

• Alessandra Potrich and Emanuele Pianta
• Fondazione Bruno Kessler - IRST
• Trento, Italy

LREC 2008
Marrakech, 31may 2008
2
Overview

• Learning ISA relations in the patent processing
  domain (the PatExpert Project)
• The L-ISA algorithm
• Evaluation
• Future Work

3
Ontology Learning/Population

• Ontology Learning acquisition of new concepts
  and relations between them
• e.g., a device is an artifact
• Ontology Population acquisition of factual
  knowledge about specific instances
• e.g. Einstein is an instance of a scientist
• e.g. Einstein was born in 1879

4
PATExpert

• Funded by the European Union
• Aim improving patent retrieval, summarization,
  paraphrasing, classification and valuing through
  shallow and deep semantic analysis
• Main semantic analysis task recognizing
  occurrences of KB concepts and relations
• Proof of the concept on two domains
• Optical Recording
• Machine Tools
• Focus of the presentation Ontology Learning in
  the Optical Recording domain

5
Optical Recording Domain Ontology (ORDO)

• Based on the Owl formalism
• Built in three stages
• 200 hundreds manually crafted concepts starting
  from a list of the most frequent terms in a
  reference corpus
• Pro-ISA ontology learning algorithm based on
  projection of WordNet fragments onto ORDO
• L-ISA ontology learning algorithm based on
  acquisition of isa templates from the Web

6
Patent Concept Annotation

• Given a target word
• disambiguate it, by assigning a WN synset whose
  domain is compatible with the optical recording
  domain (exploiting WORDNET-DOMAINS)
• If the synset is linked to an ORDO concept
  annotate the target word with the ORDO concept
• Otherwise apply Pro-ISA
• Otherwise apply L-ISA

7
Choosing the right sense

• Senses for the word CD
• 1. cadmium, Cd, atomic_number_48
  (CHEMISTRY)
• 2. candle, candela, cd, standard candle
  (PHISYCS)
• 3. certificate of deposit, CD
  (MONEY)
• 4. compact disk, compact disc, CD (COMPUTER,
  MUSIC)

8
Direct Concept Annotation
KB-concept
synset
compact_disk, compact_disc, CD
ordocd
CD
lemma
9
Pro-ISA 1Looking for a WN-to-ORDO link
event
sumoProcess
happening, occurrence, occurrent, natural_event
trouble
noise, interference, disturbance
crosstalk, XT -cross_talk, cross-talk,
crosstalk_amount
cross-talk
Lemma
10
Pro-ISA 2 Projecting ISA chains (WN -gt ORDO)
event
sumoProcess
happening, occurrence, occurrent, natural_event
auto_ordohappening
auto_ordotrouble
trouble
noise, interference, disturbance
auto_ordonoise
crosstalk, XT -cross_talk, cross-talk,
crosstalk_amount
auto_ordocrosstalk
cross-talk
11
From Pro-ISA to L-ISA

• In 15 of cases, the target word is not in
  WordNet, so Pro-ISA cannot be applied
• Then try and exploit the WEB
• Why not the patent corpus itself?
• Isa relations are not frequent in restricted
  corpora
• Patents often contain concept definitions with
  local scope
• We dont want idiosyncratic concept definitions,
  but common, shared definitions.

12
Learning ISA relations from a corpus

• by exploiting linguistic patterns expressing
  the ISA relation (Hearst, 1992 Hearst, 1998
  Mititelu, 2006)
• Many patterns have been presented in the
  literature, but
• Few evaluations of the pattern reliability
  (except Snow 2006)
• Even less task-oriented evaluation in domain
  specific, concrete application scenarios.
• This paper attempt to provide both kind of
  evaluations in a real-word, challenging scenario
  such as patent semantic analysis.

13
Lexico-Syntactic Patterns

• Patterns reported in the literature

sequence of tokens
NP1 isa-phrase NP2
syntactic noun phrases

• In our case we are looking for the hypernym of a
  specific target term

Term-NP isa-phrase Hyper-NP
Hyper-NP isa-phrase Term-NP
14
L-ISA

• Google (or any other web engine) does not allow
  for searching lexico-syntactic patterns
• So, we proceed in three steps
• Snippet acquisition from Google
• Lexico-syntactic filtering
• Semantic filtering

15
L-ISA Snippet Acquisition

• Suppose we cannot link the term photodetector
  to any ORDO concept.
• We want to exploit the following lexico-syntactic
  pattern
• ltTERM-NPgt is an ltHYPER-NPgt
• Submit to Google the following string query
• photodetector is an
• Keep the first 100 snippets (at most), e.g.
• ... upper frequencies, the PIN waveguide
  photodetector is an attractive device, since it
  is possible to reduce transit time without ..
• Transform HTML snippets in pure text.

16
L-ISA Lexico-syntactic Filtering

• Annotate snippets with TextPro (PoS, lemma,
  chunk)
• Recognize ltTerm-NPgt isa-phrase ltHyper-NPgt in the
  annotated snippets

token PoS lemma chunk
TERM-NP the AT0 the B-NP
PIN NN1 pin I-NP
waveguide NN1 waveguide I-NP
photodetector NN1 photodetector I-NP
isa-phrase is VBZ be B-VP
an AT0 an B-NP
HYPER-NP attractive AJ0 attractive I-NP
device NN1 device I-NP
17
L-ISA Lexico-syntactic Filtering

• Filter out TERM-NP
• if target term is modified (e.g. PIN waveguide
  photodetector above)
• if it looks like a proper names (e.g. uppercase
  letter in the middle of a sentence).
• Keep HYPER-NP
• only if it fits a restricted number of
  PoS-pattern
• (N AN NN NNN ANN XNN R Vpastpart
  AXN)

TERM-NP HYPER-NP
the photodetector analog signal
A photodetector apparatus
photodetector effective monitor
The photodetector electric device
a photodetector electronic device
photodetector object
18
Semantic Filtering

• Keep only those HYPER-NPs compatible with the
  Optical Recording domain, by checking
• whether the HYPER-NP is already a label in one of
  the known ontologies (SUMO, ORDO, AUTO-ORDO)
• whether it is present in a WordNet synset with a
  WORDNET-DOMAIN label compatible with the Optical
  Recording domain.

HYPER-NP IN KB IN WN DOM. COMPAT
analog signal
apparatus yes yes midlow
effective monitor
electric device
electronic device yes
object yes yes midlow
Candidate hypernyms for photodetctor
19
Candidate Selection

• Candidates are weighed according to
• Frequency and Reliability of patterns where the
  hypernym occurs
• Variety of patterns
• Belonging to specific ontologies (manual ORDO,
  AUTO-ORDO or SUMO, in decreasing preference
  order)

20
Evaluating the Reliability of ISA Patterns

• Assessement of the reliability of the patterns
  reported in the literature as predictors of the
  isa relation
• Around 80 templates
• On three target terms groove, photodetector
  and magnetic head.
• Google returned around 9.000 snippets
• Only snippets passing lexico-syntactic filtering
  have been actually manually evaluated (about
  1,450)
• Guideline try to interpret the intentions of the
  author (does he/she really intende to say that X
  isa subclass of Y, beyond inappropriate phrasing,
  and even if you know that it is not true?)
• Results of this evaluation exploited in weighting
  the hypernym candidates

21
Evaluating the L-ISA accuracy

• Measuring the accuracy of the L-ISA algorithm in
  finding the hypernym of a given domain concept
• Most frequent 100 terms that we were not able to
  link to the ORDO ontology using the Pro-ISA
  learning strategy
• Including wrong target terms (because of errors
  of the linguistic processors, e.g. a past
  participle instead of a noun)
• Accuracy 78.6

22
Future Work

• Extend evaluation set
• Inter-coder agreement
• Use Machine Learning to optimize the weights
  associated to templates