The%20Harmony%20of%20Music%20and%20Computing

1
The Harmony of Music and Computing
Expanding a Domain-Specific Database

• Jantine Trapman

2
Overview

• Components
• LT4eL
• Cornetto
• Creation / expansion of Music Ontology
• Automatic Creation
• Watson
• Prompt
• Mapping
• Music Ontology
• Cornetto

3
Components

• LT4eL
• Cornetto

4
Components LT4eL

• Language Technology for eLearning
• www.lt4el.eu
• Development of search and management facilities
  in the LMS
• Keyword Extractor
• Glossary Candidate Finder
• Semantic Search

5
Semantic Search

• Based on
• (multilingual) documents (LOs) for eight
  languages
• semantic annotation of LOs
• ontology
• lexicon for each language involved
• Corpus and ontology are restricted to Computing
  domain

6
Computing Ontology (1)

• Creation
• Manually annotated keywords in eight languages
  extracted from LOs
• Translated into (English) concepts
• Definitions collected on the WWW and added to
  concepts
• Extension with additional concepts from
• Restrictions on existing concepts
• Superconcepts of existing concepts
• Missing subconcepts
• Annotation of LOs

7
Computing Ontology (2)

• Domain ontology
• Domain Computing
• Manually created
• 1406 concepts
• 50 from DOLCE
• 250 intermediate concepts from OntoWordNet
• Use
• Lexicon development for 8 languages
• Semantic annotation LOs
• LO indexing

8
Computing Ontology Part
9
Computing Lexicon

• Concepts were translated in all languages
• Each entry contains three types of information
• Concept (and superconcept)
• CDDrive (is-a Drive)
• Definition
• a drive that reads a compact disc and that is
  connected to an audio system
• Set of terms in a given language
• CD-speler, CD drive

10
Expansion of the LT4eL KB

• Future more domains needed
• Task
• Expansion ontology and lexicons
• Preferably semi-automatic
• Three options
• Top-down
• Bottom-up
• Both, ingredients
• Cornetto, WordNet
• Music ontology
• Watson, Prompt

11
Cornetto

• Combinatorial and Relational
• Network as Toolkit for Dutch Language Technology
• Referentie Bestand Nederlands (RBN)
• ? lexical units
• Dutch part of EuroWordNet
• Dutch WordNet (DWN)
• ? synsets
• SUMO/MILO plus extensions
• ? terms and axioms
• Core table of Cornetto Identifiers (CIDs)

http//www.let.vu.nl/onderzoek/projectsites/cornet
to/index.html
12
Example Lexical Entry Cornetto (1)
noun zanger noun zanger
Sense CID
Iemand die zingt c_n-42316
Vogel die zingt c_n-42317
(Poëtisch voor) dichter c_n-42318

13
noun zanger1 c_n-42316

• Morphology
• typederivation structurezingener
  plurformszangers
• Syntax
• genderm/f articlede
• Semantics
• referencecommon countabilitycount
  typehuman subclassberoepsnaam/beoefenaar
  resumeiemand die zingt
• Pragmatics
• domainmuz

14
Example Lexical Entry Cornetto (2)

• Combinatorics zanger1
• De redacteur van het woordenboek was ook een
  zanger
• De zanger van de band
• SUMO (, , hasSkill)
• Synonyms
• zanger, zangeres
• HAS_HYPERONYM musicus, musicienne, muzikant
• HAS_HYPONYM baszanger, sopraan, blueszanger,
  charmezanger, ...
• Equivalence relations EQ_SYNONYM singer,
  vocalist, vocalizer, vocaliser /ENG20-09908715-n ?
  link with WordNet 2.0!
• WordNet Domains music

15
Goal
16
Tasks

• Extract music related terms from Cornetto
• Create a domain ontology for Music
• Map between terms from lexicon and concepts in
  ontology
• Map music ontology to OntoWN and DOLCE
• Adjust Cornetto data to LT4eL format

17
Questions (1)

1. How can we automatize the process of ontology
   building and to which extent?
2. How can we profit from existing resources from
   the Semantic Web to enrich ontologies?
3. To which extent do Watson and PROMPT support the
   reuse of existing resources?

18
Music Ontology

• Automatic Creation
• Expansion with
• Watson
• Prompt

19
Automatic Creation (1)

• (Basili et al. 2007) automatic ontology
  extraction from open-domain corpus (BNC)
• Designed for three tasks
• lexical ambiguity resolution within a specific
  domain
• restricting a set of terms to a subset relevant
  for an ontology to be constructed
• expanding this new ontology with other, novel and
  relevant concepts, relations and instances.

20
Automatic Creation (2)

• Preprocessing
• Corpus split in 40 sentence text segments
• PoS tagging
• Filtering of noun phrases
• General steps
• Term extraction through Latent Semantic Analysis
  (Deerwester et al. 1990)
• Ontology extraction from WordNet based on
  Conceptual Density (Agirre and Rigau 1996)

21
Music Ontology Part
22
Music Ontology (Basili et al. 07)

• 46 primitive classes
• Leaf concepts have a synset ID from WordNet
• No properties, only super-/subconcept relation
• So.. a rather small and shallow ontology
• expansion by exploiting Semantic Web techniques

23
(No Transcript)
24
Watson (1)

• http//watson.kmi.open.ac.uk/WatsonWUI/
• Every URI is clickable all resources are
  available
• Information about
• Size
• Representation language
• Number of classes, properties, individuals etc.
• Review rating
• Interface for SPARQL queries
• Possibility of (upwards) navigation

25
Watson (2)

• Also available as
• Protégé plug-in (under development)
• API
• New concepts can be added
• Manually
• One by one
• Much human action required
• Faster than creation from scratch, but still a
  tedious exercise

26
Watson (3)

• Watson provides in
• a list of URIs of available semantic databases
• a list of candidate concepts
• What is still lacking
• a (semi-)automatic way to merge or align new
  concepts or ontologies to an existing one.
• Possible solution Prompt

27
PROMPT (1)

• http//protege.stanford.edu/plugins/prompt/prompt.
  html
• Protégé plug-in
• Functionalities
• Comparison
• Inclusion
• Merging
• Alignment
• Requirement ontologies for merge etc. must be
  available offline
• Prompt goes beyond purely syntactic matching
• Evaluation shows that experts followed 90 of
  Prompts suggestions

28
Prompt (2)

• Saves time and effort
• linguistically similar classes are found quickly
• inherited properties and subclasses can be added
  automatically
• similar structures are automatically detected
• automatic consistency check
• Resources must have the exact same markup
  language
• Merging
• faster but more complex
• requires good insight in resources

29
Mapping

• Music Ontology
• Cornetto

30
Resources

• Music Ontology
• Some nodes have WordNet ID (from the automatic
  process
• Many havent, especially those added with Watson
• Cornetto entries
• have synset ID from Dutch WN
• have mapping to WordNet entry through equivalence
  or near-equivalence e.g.

31
Questions (2)

• To which extent does WordNet support a mapping
  between
• The Cornetto lexicon and a newly created ontology
  partly based on Wordnet
• The existing ontology and lexicon from LT4eL, and
  Cornetto ontology

32
Procedures

• A concept either has or has not a WN synset ID
• Mapping via WordNet synset ID
• Lookup synset ID in Cornetto
• Establish related DWN synset(s)
• Results until now without problems although
  near-equivalence relations are expected to give
  mismatches
• Mapping without synset ID
• Syntactic matching of conceptname with terms from
  WordNet synsets
• compare definitions and glosses

33
Examples easy match

• zanger1 d_n-20810 (iemand die zingt) is
• EQ_SYNONYM of
• singer, vocalist, vocalizer, vocaliser
  /ENG20-09908715-n (a person who sings )
• strijkkwartet1 d_n-14287
• (ensemble van vier strijkers) and
• strijkkwartet2 d n-19905
• (ensemble voor vier strijkers) are
• EQ_NEAR_SYNONYM of
• soloist1/ENG20-09931035
• Note Cornetto contains mismatch between WN and
  DWN

34
Matching without ID (1)

• For each owlClass in Music ontology
• try to match with
• target attribute in relation element of Cornetto
  XML structure, where
• Attribute relation_name is (EQ_)NEAR_SYNONYM e.g.
• Add synset ID to concept (for mapping to
  OntoWordNet)
• ltowlClass rdfabouthttp///myOntos/music.owlor
  chestra"/gt
• ltrelation relation_name"EQ_NEAR_SYNONYM"
  target20-previewtext"symphony orchestra1,
  symphony2" version"pwn_1_6" target20"ENG20-0775
  0308-n" target"ENG16-06123240-n"gt

35
Matching without ID (2)

• Compare definitions and glosses
• many ontology classes have a definition
• each WN synset has a gloss
• preprocess stemming and filtering nouns
• Consider percentage of nouns in concept
  definition that match with a certain gloss
• Evaluate results
• Note some definitions are equal to WN glosses

36
Current work

• Matching without ID on class name and
  definitions/glosses
• Manually check results for precision and recall
• Problem MWEs, e.g. class Brass_Instrument
• has no precise WN counterpart, but
• Brass does exist, but
• it has multiple senses ? how can we disambiguate?
• Question ID allows easy and reliable match, but
  can we do the task without?

37
Remaining and Future work

• Attuning format lexicon to LT4eL format
• Mapping to OntoWordNet (semi-automatic)
• Mapping to DOLCE (manual task)
• Ontology evaluation
• Experiments with WordNets from different
  languages
• Involve additional lexical info to improve LT4eL
  search engine e.g. use morphological info about
  plural forms