SlideShare a Scribd company logo
1 of 22
Semantic Parsing 
Definition: process of mapping natural language 
text into a formal representation of its meaning. 
Ewan forgot the mozzarella in his car. 
∃x0 named(x0, ewan, person) ∧ 
∃x1 mozzarella(x1) ∧ 
∃x2 car(x2) ∧ of(x2,x0) ∧ in(x1, x2) ∧ 
∃e event(e) ∧ forget(e) ∧ agent(e, x0) ∧ 
patient(e, x1) 
10 September 2014 2
Semantic Parsing 
Definition: process of mapping natural language 
text into a formal representation of its meaning. 
Ewan forgot the mozzarella in his car. 
∃x0 named(x0, ewan, person) ∧ 
∃x1 mozzarella(x1) ∧ 
∃x2 car(x2) ∧ of(x2,x0) ∧ in(x1, x2) ∧ 
∃e event(e) ∧ forget(e) ∧ agent(e, x0) ∧ 
patient(e, x1) 
10 September 2014 3
Semantic Role Labelling 
Mapping to a shallow semantic representation of 
predicates and associated semantic arguments 
Ewan forgot the mozzarella in his car. 
∃x0 named(x0, ewan, person) ∧ 
∃x1 mozzarella(x1) ∧ 
∃x2 car(x2) ∧ of(x2,x0) ∧ in(x1, x2) ∧ 
∃e event(e) ∧ forget(e) ∧ agent(e, x0) ∧ 
patient(e, x1) 
10 September 2014 4
Semantic Role Labelling 
Mapping to a shallow semantic representation of 
predicates and associated semantic arguments 
Ewan forgot the mozzarella in his car. 
∃x0 named(x0, ewan, per) ∧ male(x0) ∧ 
∃x1 mozzarella(x1) ∧ 
∃x2 car(car←———x2) ∧ of(his x2,x0) ∧ 
∧ 
∃e event(e) ∧ forget(e) ∧ agent(e, x0) ∧ 
Ewan—actor→forget) 
Ewan———↗ patient(e, x3) ∧ ↖ in(———e, x2) 
mozzarella 
10 September 2014 5
Semantic Role Labelling 
Mapping to a shallow semantic representation of 
predicates and associated semantic arguments 
Ewan forgot the mozzarella in his car. 
∃x0 named(x0, ewan, per) ∧ male(x0) ∧ 
∃x1 mozzarella(x1) ∧ 
∃x2 car←car(x2) owner—∧ of(x2,his x0) ∧ 
car—location ∧ 
∃e event(e) ∧ forget(e) ∧ agent(e, x0) ∧ 
Ewan—actor→forget) ↓ 
Ewan—patient(actor↗ e, x3) ∧ in(↖theme—e, x2) 
mozzarella 
10 September 2014 6
Semantic Role Labelling 
Motivation: identify who did what to whom, 
where, why and how, etc. 
Ewan forgot the mozzarella in his car. 
∃x0 named(x0, ewan, per) ∧ male(x0) ∧ 
∃x1 mozzarella(x1) ∧ 
∃x2 car(car←x2) owner—∧ of(x2,his x0) ∧ 
car—location ∧ 
∃e event(e) ∧ forget(e) ∧ agent(e, x0) ∧ 
Ewan—actor→forget) ↓ 
Ewan—patient(actor↗ e, x3) ∧ in(↖theme—e, x2) 
mozzarella 
10 September 2014 7
S-CASE Project 
CASE: Computer Assisted Software Engineering 
 Plethora of software solutions already available 
 Could be (re)used for rapid prototyping 
The role of UEDIN in this project: 
 Analyse textual requirements of existing 
solutions that describe their functionalities 
 Provide a search interface for finding solutions 
10 September 2014 8
Functional Requirements 
Properties 
 Discussed by developers and customers 
 Basis for work plans, implementations, etc. 
Examples 
“The user must be able to login to his account.” 
“The system should store all activities.” 
… 
10 September 2014 9
Pre-processing 
Before mapping text to meaning representations: 
 Tokenization 
 Part-of-speech tagging and lemmatization 
 Syntactic dependency parsing 
“The user must be able to login to his account.” 
The user must be able to login to his account . 
the 
user 
must 
be 
able 
to 
login 
to 
his 
account 
. 
DT 
NN 
MD 
VB 
JJ 
TO 
VB 
TO 
PRP 
NN 
. 
10 September 2014 10
Semantic Analysis 
Several steps of analysis are required 
 Find “predicates” in a sentence 
 Identify potential arguments 
 Classify arguments of each predicate 
“The user must be able to login to his account.” 
The user must be able to login to his account . 
the 
user 
must 
be 
able 
to 
login 
to 
his 
account 
. 
DT 
NN 
MD 
VB 
JJ 
TO 
VB 
TO 
PRP 
NN 
. 
10 September 2014 11
Semantic Analysis—Detailed View 
Several steps of analysis are required 
 Find “predicates” in a sentence 
 Identify potential arguments 
 Classify arguments of each predicate 
“The user must be able to login to his account.” 
 Assigned part-of-speech 
 Number of children 
 Parent word form 
The user must be able to login to his account . 
the 
user 
must 
be 
able 
to 
login 
to 
his 
account 
. 
DT 
NN 
MD 
VB 
JJ 
TO 
VB 
TO 
PRP 
NN 
. 
10 September 2014 12
Semantic Analysis—Detailed View 
Several steps of analysis are required 
 Find “predicates” in a sentence 
 Identify potential arguments 
 Classify arguments of each predicate 
“The user must be able to login to his account.” 
 Assigned part-of-speech 
 Labelled path to predicate 
 (Other) children of pred 
The user must be able to login to his account . 
the 
user 
must 
be 
able 
to 
login 
to 
his 
account 
. 
DT 
NN 
MD 
VB 
JJ 
TO 
VB 
TO 
PRP 
NN 
. 
10 September 2014 13
Semantic Analysis—Detailed View 
Several steps of analysis are required 
 Find “predicates” in a sentence 
 Identify potential arguments 
 Classify arguments of each predicate 
“The user must be able to login to his account.” 
 Head word of argument 
 Relative position 
 Labelled dependency 
The user must be able to login to his account . 
the 
user 
must 
be 
able 
to 
login 
to 
his 
account 
. 
DT 
NN 
MD 
VB 
JJ 
TO 
VB 
TO 
PRP 
NN 
. 
10 September 2014 14
What about Linked Data? 
Once we identified all predicates and arguments 
 We can map them into a structured format 
 Link with other information and share online 
 Store in a database for downstream applications 
“The user must be able to login to his account.” 
The user must be able to login to his account . 
the 
user 
must 
be 
able 
to 
login 
to 
his 
account 
. 
DT 
NN 
MD 
VB 
JJ 
TO 
VB 
TO 
PRP 
NN 
. 
10 September 2014 15
The user must be able to login to his account . 
the 
:x0 user 
a :must 
user; be 
able 
:e0 to 
login 
a :to 
login; 
his 
account 
. 
DT 
:actor_NN 
of :e0. MD 
VB 
JJ 
TO 
:has_actor VB 
:TO 
x0; 
PRP 
NN 
. 
RDF Representation 
Storing SRL predicates and arguments 
 Define one entity per relevant word token 
(predicates and arguments can coincide) 
 Use RDF triples to describe relations 
“The user must be able to login to his account.” 
user login 
:acts_on :x1. 
10 September 2014 16
The user must be able to login to his account . 
the 
:x0 user 
a :must 
user; be 
able 
:e0 to 
login 
a :to 
login; 
his 
account 
. 
DT 
:actor_NN 
of :e0. MD 
VB 
JJ 
TO 
:has_actor VB 
:TO 
x0; 
PRP 
NN 
. 
RDF Representation (cont.) 
The bigger scheme: what are users, logins, etc.? 
 Ontology defines classes, relations, restrictions 
 user is-a actor is-a thingtype is-a concept 
 ACTOR_OF(x, y) ↔ HAS_ACTOR(y, x) 
“The user must be able to login to his account.” 
_:user _:login 
:acts_on :x1. 
10 September 2014 17
Advantages for Applications 
 Ontology defines concept types and relations 
 Finite set of pre-defined symbols 
 user is-a actor is-a thingtype is-a concept 
 subclasses can be exploited for search 
 ACTOR_OF(x, y) ↔ HAS_ACTOR(y, x) 
 Axioms for detecting inconsistencies 
and inferring missing relations 
10 September 2014 18
Putting the Pieces Together 
OWL 
Ontology 
Applications 
Applications 
Requirements 
Document 
Implemented 
Software 
Component 
RDF 
Triples 
DB 
10 September 2014 19
Conclusions 
 Semantic parsing is an important prerequisite for 
computational natural language understanding 
 Results of shallow semantic analysis can be 
represented in a structured format for 
downstream applications 
 Linked data helps us to connect and share 
information on existing software solutions and 
makes efficient search possible 
10 September 2014 20
21 
Thank you! 
10 September 2014
22 
Questions? 
10 September 2014

More Related Content

Viewers also liked

Viewers also liked (20)

Programa Mais Educação _ Relatório das Atividades _ 2º bimestre
Programa Mais Educação _ Relatório das Atividades _  2º bimestrePrograma Mais Educação _ Relatório das Atividades _  2º bimestre
Programa Mais Educação _ Relatório das Atividades _ 2º bimestre
 
Transformer
TransformerTransformer
Transformer
 
Projeto Rádio Escolar
Projeto Rádio EscolarProjeto Rádio Escolar
Projeto Rádio Escolar
 
Seven types of ambiguity
Seven types of ambiguity Seven types of ambiguity
Seven types of ambiguity
 
Características do rádio
Características do rádioCaracterísticas do rádio
Características do rádio
 
Supermarket
SupermarketSupermarket
Supermarket
 
A história do rádio
A história do rádioA história do rádio
A história do rádio
 
Radio e audio__revisao
Radio e audio__revisaoRadio e audio__revisao
Radio e audio__revisao
 
Mídia IELUSC - Meio Rádio
Mídia IELUSC - Meio RádioMídia IELUSC - Meio Rádio
Mídia IELUSC - Meio Rádio
 
Apresentacao Radio Ondas
Apresentacao Radio OndasApresentacao Radio Ondas
Apresentacao Radio Ondas
 
Aula rádio
Aula rádioAula rádio
Aula rádio
 
Cieja roteiro para radio
Cieja roteiro para radioCieja roteiro para radio
Cieja roteiro para radio
 
Rádio
RádioRádio
Rádio
 
mídias digitais
mídias digitaismídias digitais
mídias digitais
 
Supermarkets
SupermarketsSupermarkets
Supermarkets
 
Bab 7
Bab 7Bab 7
Bab 7
 
Script tv modelo_agenciade_noticias
Script tv modelo_agenciade_noticiasScript tv modelo_agenciade_noticias
Script tv modelo_agenciade_noticias
 
A radio
A radioA radio
A radio
 
Atividades - Oficina Rádio Escola
Atividades - Oficina Rádio EscolaAtividades - Oficina Rádio Escola
Atividades - Oficina Rádio Escola
 
Roteiro Para Radialistas
Roteiro Para RadialistasRoteiro Para Radialistas
Roteiro Para Radialistas
 

Similar to Semantic Parsing and Representation for Software Requirements

CrossLanguageSpotter: A Library for Detecting Relations in Polyglot Frameworks
CrossLanguageSpotter: A Library for Detecting Relations in Polyglot FrameworksCrossLanguageSpotter: A Library for Detecting Relations in Polyglot Frameworks
CrossLanguageSpotter: A Library for Detecting Relations in Polyglot FrameworksGiuseppe Rizzo
 
Chat Bots with Amazon Lex - AWS Summit SG 2017
Chat Bots with Amazon Lex  - AWS Summit SG 2017Chat Bots with Amazon Lex  - AWS Summit SG 2017
Chat Bots with Amazon Lex - AWS Summit SG 2017Amazon Web Services
 
Coulda Been a Contributor: Making a difference with Open Source Software - OS...
Coulda Been a Contributor: Making a difference with Open Source Software - OS...Coulda Been a Contributor: Making a difference with Open Source Software - OS...
Coulda Been a Contributor: Making a difference with Open Source Software - OS...Vanessa Hurst
 
Coulda Been a Contributor: Making a difference with Open Source Software - OS...
Coulda Been a Contributor: Making a difference with Open Source Software - OS...Coulda Been a Contributor: Making a difference with Open Source Software - OS...
Coulda Been a Contributor: Making a difference with Open Source Software - OS...CodeMontage
 

Similar to Semantic Parsing and Representation for Software Requirements (6)

CrossLanguageSpotter: A Library for Detecting Relations in Polyglot Frameworks
CrossLanguageSpotter: A Library for Detecting Relations in Polyglot FrameworksCrossLanguageSpotter: A Library for Detecting Relations in Polyglot Frameworks
CrossLanguageSpotter: A Library for Detecting Relations in Polyglot Frameworks
 
Query Understanding
Query UnderstandingQuery Understanding
Query Understanding
 
Owlizr
OwlizrOwlizr
Owlizr
 
Chat Bots with Amazon Lex - AWS Summit SG 2017
Chat Bots with Amazon Lex  - AWS Summit SG 2017Chat Bots with Amazon Lex  - AWS Summit SG 2017
Chat Bots with Amazon Lex - AWS Summit SG 2017
 
Coulda Been a Contributor: Making a difference with Open Source Software - OS...
Coulda Been a Contributor: Making a difference with Open Source Software - OS...Coulda Been a Contributor: Making a difference with Open Source Software - OS...
Coulda Been a Contributor: Making a difference with Open Source Software - OS...
 
Coulda Been a Contributor: Making a difference with Open Source Software - OS...
Coulda Been a Contributor: Making a difference with Open Source Software - OS...Coulda Been a Contributor: Making a difference with Open Source Software - OS...
Coulda Been a Contributor: Making a difference with Open Source Software - OS...
 

Recently uploaded

Spermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSpermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSarthak Sekhar Mondal
 
Disentangling the origin of chemical differences using GHOST
Disentangling the origin of chemical differences using GHOSTDisentangling the origin of chemical differences using GHOST
Disentangling the origin of chemical differences using GHOSTSérgio Sacani
 
Zoology 4th semester series (krishna).pdf
Zoology 4th semester series (krishna).pdfZoology 4th semester series (krishna).pdf
Zoology 4th semester series (krishna).pdfSumit Kumar yadav
 
Biological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfBiological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfmuntazimhurra
 
Isotopic evidence of long-lived volcanism on Io
Isotopic evidence of long-lived volcanism on IoIsotopic evidence of long-lived volcanism on Io
Isotopic evidence of long-lived volcanism on IoSérgio Sacani
 
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls AgencyHire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls AgencySheetal Arora
 
Botany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdfBotany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdfSumit Kumar yadav
 
Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...
Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...
Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...jana861314
 
Chromatin Structure | EUCHROMATIN | HETEROCHROMATIN
Chromatin Structure | EUCHROMATIN | HETEROCHROMATINChromatin Structure | EUCHROMATIN | HETEROCHROMATIN
Chromatin Structure | EUCHROMATIN | HETEROCHROMATINsankalpkumarsahoo174
 
VIRUSES structure and classification ppt by Dr.Prince C P
VIRUSES structure and classification ppt by Dr.Prince C PVIRUSES structure and classification ppt by Dr.Prince C P
VIRUSES structure and classification ppt by Dr.Prince C PPRINCE C P
 
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptx
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptxSOLUBLE PATTERN RECOGNITION RECEPTORS.pptx
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptxkessiyaTpeter
 
Recombination DNA Technology (Nucleic Acid Hybridization )
Recombination DNA Technology (Nucleic Acid Hybridization )Recombination DNA Technology (Nucleic Acid Hybridization )
Recombination DNA Technology (Nucleic Acid Hybridization )aarthirajkumar25
 
DIFFERENCE IN BACK CROSS AND TEST CROSS
DIFFERENCE IN  BACK CROSS AND TEST CROSSDIFFERENCE IN  BACK CROSS AND TEST CROSS
DIFFERENCE IN BACK CROSS AND TEST CROSSLeenakshiTyagi
 
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...ssifa0344
 
Animal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptxAnimal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptxUmerFayaz5
 
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCR
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCRStunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCR
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCRDelhi Call girls
 
Botany krishna series 2nd semester Only Mcq type questions
Botany krishna series 2nd semester Only Mcq type questionsBotany krishna series 2nd semester Only Mcq type questions
Botany krishna series 2nd semester Only Mcq type questionsSumit Kumar yadav
 
GBSN - Biochemistry (Unit 1)
GBSN - Biochemistry (Unit 1)GBSN - Biochemistry (Unit 1)
GBSN - Biochemistry (Unit 1)Areesha Ahmad
 
Green chemistry and Sustainable development.pptx
Green chemistry  and Sustainable development.pptxGreen chemistry  and Sustainable development.pptx
Green chemistry and Sustainable development.pptxRajatChauhan518211
 

Recently uploaded (20)

Spermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSpermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
 
Disentangling the origin of chemical differences using GHOST
Disentangling the origin of chemical differences using GHOSTDisentangling the origin of chemical differences using GHOST
Disentangling the origin of chemical differences using GHOST
 
Zoology 4th semester series (krishna).pdf
Zoology 4th semester series (krishna).pdfZoology 4th semester series (krishna).pdf
Zoology 4th semester series (krishna).pdf
 
Biological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfBiological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdf
 
Isotopic evidence of long-lived volcanism on Io
Isotopic evidence of long-lived volcanism on IoIsotopic evidence of long-lived volcanism on Io
Isotopic evidence of long-lived volcanism on Io
 
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls AgencyHire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
Hire 💕 9907093804 Hooghly Call Girls Service Call Girls Agency
 
Botany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdfBotany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdf
 
Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...
Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...
Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...
 
Chromatin Structure | EUCHROMATIN | HETEROCHROMATIN
Chromatin Structure | EUCHROMATIN | HETEROCHROMATINChromatin Structure | EUCHROMATIN | HETEROCHROMATIN
Chromatin Structure | EUCHROMATIN | HETEROCHROMATIN
 
VIRUSES structure and classification ppt by Dr.Prince C P
VIRUSES structure and classification ppt by Dr.Prince C PVIRUSES structure and classification ppt by Dr.Prince C P
VIRUSES structure and classification ppt by Dr.Prince C P
 
9953056974 Young Call Girls In Mahavir enclave Indian Quality Escort service
9953056974 Young Call Girls In Mahavir enclave Indian Quality Escort service9953056974 Young Call Girls In Mahavir enclave Indian Quality Escort service
9953056974 Young Call Girls In Mahavir enclave Indian Quality Escort service
 
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptx
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptxSOLUBLE PATTERN RECOGNITION RECEPTORS.pptx
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptx
 
Recombination DNA Technology (Nucleic Acid Hybridization )
Recombination DNA Technology (Nucleic Acid Hybridization )Recombination DNA Technology (Nucleic Acid Hybridization )
Recombination DNA Technology (Nucleic Acid Hybridization )
 
DIFFERENCE IN BACK CROSS AND TEST CROSS
DIFFERENCE IN  BACK CROSS AND TEST CROSSDIFFERENCE IN  BACK CROSS AND TEST CROSS
DIFFERENCE IN BACK CROSS AND TEST CROSS
 
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
TEST BANK For Radiologic Science for Technologists, 12th Edition by Stewart C...
 
Animal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptxAnimal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptx
 
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCR
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCRStunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCR
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCR
 
Botany krishna series 2nd semester Only Mcq type questions
Botany krishna series 2nd semester Only Mcq type questionsBotany krishna series 2nd semester Only Mcq type questions
Botany krishna series 2nd semester Only Mcq type questions
 
GBSN - Biochemistry (Unit 1)
GBSN - Biochemistry (Unit 1)GBSN - Biochemistry (Unit 1)
GBSN - Biochemistry (Unit 1)
 
Green chemistry and Sustainable development.pptx
Green chemistry  and Sustainable development.pptxGreen chemistry  and Sustainable development.pptx
Green chemistry and Sustainable development.pptx
 

Semantic Parsing and Representation for Software Requirements

  • 1.
  • 2. Semantic Parsing Definition: process of mapping natural language text into a formal representation of its meaning. Ewan forgot the mozzarella in his car. ∃x0 named(x0, ewan, person) ∧ ∃x1 mozzarella(x1) ∧ ∃x2 car(x2) ∧ of(x2,x0) ∧ in(x1, x2) ∧ ∃e event(e) ∧ forget(e) ∧ agent(e, x0) ∧ patient(e, x1) 10 September 2014 2
  • 3. Semantic Parsing Definition: process of mapping natural language text into a formal representation of its meaning. Ewan forgot the mozzarella in his car. ∃x0 named(x0, ewan, person) ∧ ∃x1 mozzarella(x1) ∧ ∃x2 car(x2) ∧ of(x2,x0) ∧ in(x1, x2) ∧ ∃e event(e) ∧ forget(e) ∧ agent(e, x0) ∧ patient(e, x1) 10 September 2014 3
  • 4. Semantic Role Labelling Mapping to a shallow semantic representation of predicates and associated semantic arguments Ewan forgot the mozzarella in his car. ∃x0 named(x0, ewan, person) ∧ ∃x1 mozzarella(x1) ∧ ∃x2 car(x2) ∧ of(x2,x0) ∧ in(x1, x2) ∧ ∃e event(e) ∧ forget(e) ∧ agent(e, x0) ∧ patient(e, x1) 10 September 2014 4
  • 5. Semantic Role Labelling Mapping to a shallow semantic representation of predicates and associated semantic arguments Ewan forgot the mozzarella in his car. ∃x0 named(x0, ewan, per) ∧ male(x0) ∧ ∃x1 mozzarella(x1) ∧ ∃x2 car(car←———x2) ∧ of(his x2,x0) ∧ ∧ ∃e event(e) ∧ forget(e) ∧ agent(e, x0) ∧ Ewan—actor→forget) Ewan———↗ patient(e, x3) ∧ ↖ in(———e, x2) mozzarella 10 September 2014 5
  • 6. Semantic Role Labelling Mapping to a shallow semantic representation of predicates and associated semantic arguments Ewan forgot the mozzarella in his car. ∃x0 named(x0, ewan, per) ∧ male(x0) ∧ ∃x1 mozzarella(x1) ∧ ∃x2 car←car(x2) owner—∧ of(x2,his x0) ∧ car—location ∧ ∃e event(e) ∧ forget(e) ∧ agent(e, x0) ∧ Ewan—actor→forget) ↓ Ewan—patient(actor↗ e, x3) ∧ in(↖theme—e, x2) mozzarella 10 September 2014 6
  • 7. Semantic Role Labelling Motivation: identify who did what to whom, where, why and how, etc. Ewan forgot the mozzarella in his car. ∃x0 named(x0, ewan, per) ∧ male(x0) ∧ ∃x1 mozzarella(x1) ∧ ∃x2 car(car←x2) owner—∧ of(x2,his x0) ∧ car—location ∧ ∃e event(e) ∧ forget(e) ∧ agent(e, x0) ∧ Ewan—actor→forget) ↓ Ewan—patient(actor↗ e, x3) ∧ in(↖theme—e, x2) mozzarella 10 September 2014 7
  • 8. S-CASE Project CASE: Computer Assisted Software Engineering  Plethora of software solutions already available  Could be (re)used for rapid prototyping The role of UEDIN in this project:  Analyse textual requirements of existing solutions that describe their functionalities  Provide a search interface for finding solutions 10 September 2014 8
  • 9. Functional Requirements Properties  Discussed by developers and customers  Basis for work plans, implementations, etc. Examples “The user must be able to login to his account.” “The system should store all activities.” … 10 September 2014 9
  • 10. Pre-processing Before mapping text to meaning representations:  Tokenization  Part-of-speech tagging and lemmatization  Syntactic dependency parsing “The user must be able to login to his account.” The user must be able to login to his account . the user must be able to login to his account . DT NN MD VB JJ TO VB TO PRP NN . 10 September 2014 10
  • 11. Semantic Analysis Several steps of analysis are required  Find “predicates” in a sentence  Identify potential arguments  Classify arguments of each predicate “The user must be able to login to his account.” The user must be able to login to his account . the user must be able to login to his account . DT NN MD VB JJ TO VB TO PRP NN . 10 September 2014 11
  • 12. Semantic Analysis—Detailed View Several steps of analysis are required  Find “predicates” in a sentence  Identify potential arguments  Classify arguments of each predicate “The user must be able to login to his account.”  Assigned part-of-speech  Number of children  Parent word form The user must be able to login to his account . the user must be able to login to his account . DT NN MD VB JJ TO VB TO PRP NN . 10 September 2014 12
  • 13. Semantic Analysis—Detailed View Several steps of analysis are required  Find “predicates” in a sentence  Identify potential arguments  Classify arguments of each predicate “The user must be able to login to his account.”  Assigned part-of-speech  Labelled path to predicate  (Other) children of pred The user must be able to login to his account . the user must be able to login to his account . DT NN MD VB JJ TO VB TO PRP NN . 10 September 2014 13
  • 14. Semantic Analysis—Detailed View Several steps of analysis are required  Find “predicates” in a sentence  Identify potential arguments  Classify arguments of each predicate “The user must be able to login to his account.”  Head word of argument  Relative position  Labelled dependency The user must be able to login to his account . the user must be able to login to his account . DT NN MD VB JJ TO VB TO PRP NN . 10 September 2014 14
  • 15. What about Linked Data? Once we identified all predicates and arguments  We can map them into a structured format  Link with other information and share online  Store in a database for downstream applications “The user must be able to login to his account.” The user must be able to login to his account . the user must be able to login to his account . DT NN MD VB JJ TO VB TO PRP NN . 10 September 2014 15
  • 16. The user must be able to login to his account . the :x0 user a :must user; be able :e0 to login a :to login; his account . DT :actor_NN of :e0. MD VB JJ TO :has_actor VB :TO x0; PRP NN . RDF Representation Storing SRL predicates and arguments  Define one entity per relevant word token (predicates and arguments can coincide)  Use RDF triples to describe relations “The user must be able to login to his account.” user login :acts_on :x1. 10 September 2014 16
  • 17. The user must be able to login to his account . the :x0 user a :must user; be able :e0 to login a :to login; his account . DT :actor_NN of :e0. MD VB JJ TO :has_actor VB :TO x0; PRP NN . RDF Representation (cont.) The bigger scheme: what are users, logins, etc.?  Ontology defines classes, relations, restrictions  user is-a actor is-a thingtype is-a concept  ACTOR_OF(x, y) ↔ HAS_ACTOR(y, x) “The user must be able to login to his account.” _:user _:login :acts_on :x1. 10 September 2014 17
  • 18. Advantages for Applications  Ontology defines concept types and relations  Finite set of pre-defined symbols  user is-a actor is-a thingtype is-a concept  subclasses can be exploited for search  ACTOR_OF(x, y) ↔ HAS_ACTOR(y, x)  Axioms for detecting inconsistencies and inferring missing relations 10 September 2014 18
  • 19. Putting the Pieces Together OWL Ontology Applications Applications Requirements Document Implemented Software Component RDF Triples DB 10 September 2014 19
  • 20. Conclusions  Semantic parsing is an important prerequisite for computational natural language understanding  Results of shallow semantic analysis can be represented in a structured format for downstream applications  Linked data helps us to connect and share information on existing software solutions and makes efficient search possible 10 September 2014 20
  • 21. 21 Thank you! 10 September 2014
  • 22. 22 Questions? 10 September 2014

Editor's Notes

  1. Hello and thank you all for coming. My name is Michael Roth and for the next 20 minutes, or so, I will be talking about Semantic Parsing to Linked Data. The talk is mostly about parsing but I will get back to how that relates to linked data towards the end.
  2. So the first question that some of you might ask themselves now is: what is “semantic parsing”? Well, let’s start with a definition. “Semantic Parsing is … into … “. Since this is a very general definition, let’s have a look at a very specific example.
  3. It can be quite challenging to deduce a full logical representation from a sentence. For example, when looking at the text, we do not see any of the existential quantifiers from the logical representation and it’s not always clear why they should be used over universal quantifiers. On the representation side, we can see a very mixed granularity of logical predicates: they can denote specific types of entities such as mozzarella but also very general relations such as “in” or “of”.
  4. A more general variant invented by computational linguistics is a task called semantic role labelling. The idea of this task is still to perform some form of semantic parsing but instead of mapping to logical representations, we here focus on the identification of predicate-argument structures that can be observed as linguistic units.
  5. This means that a predicate, rather than being an abstract concept, is simply a word with a specific sense that can be observed in text. Typically, a predicate identified text has one or more arguments. For example, “car” and “forget” are predicates and their semantic arguments are those words or spans of words that further specify them in text. Computational linguistics came up with a somewhat here associate each of them with a specific thematic relation. For example, …
  6. To go one step further than this, approaches to semantic role labelling make use of a predefined set of roles that specify how an argument is related to the predicate.
  7. And the motivation for this is… So in addition to representing the general structure of a sentence, we can now make some inferences about the actual meaning of a sentence.