QuerioDALI: Question Answering Over Dynamic and Linked Knowledge Graphs View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2016-09-23

AUTHORS

Vanessa Lopez , Pierpaolo Tommasi , Spyros Kotoulas , Jiewen Wu

ABSTRACT

We present a domain-agnostic system for Question Answering over multiple semi-structured and possibly linked datasets without the need of a training corpus. The system is motivated by an industry use-case where Enterprise Data needs to be combined with a large body of Open Data to fulfill information needs not satisfied by prescribed application data models. Our proposed Question Answering pipeline combines existing components with novel methods to perform, in turn, linguistic analysis of a query, named entity extraction, entity/graph search, fusion and ranking of possible answers. We evaluate QuerioDALI with two open-domain benchmarks and a biomedical one over Linked Open Data sources, and show that our system produces comparable results to systems that require training data and are domain-dependent. In addition, we analyze the current challenges and shortcomings. More... »

PAGES

363-382

Book

TITLE

The Semantic Web – ISWC 2016

ISBN

978-3-319-46546-3
978-3-319-46547-0

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-319-46547-0_32

DOI

http://dx.doi.org/10.1007/978-3-319-46547-0_32

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1084843894


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0806", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information Systems", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Smarter Cities Technology Centre, IBM Research, Dublin, Ireland", 
          "id": "http://www.grid.ac/institutes/grid.424816.d", 
          "name": [
            "Smarter Cities Technology Centre, IBM Research, Dublin, Ireland"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Lopez", 
        "givenName": "Vanessa", 
        "id": "sg:person.011057446515.94", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011057446515.94"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Smarter Cities Technology Centre, IBM Research, Dublin, Ireland", 
          "id": "http://www.grid.ac/institutes/grid.424816.d", 
          "name": [
            "Smarter Cities Technology Centre, IBM Research, Dublin, Ireland"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Tommasi", 
        "givenName": "Pierpaolo", 
        "id": "sg:person.010622151751.15", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010622151751.15"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Smarter Cities Technology Centre, IBM Research, Dublin, Ireland", 
          "id": "http://www.grid.ac/institutes/grid.424816.d", 
          "name": [
            "Smarter Cities Technology Centre, IBM Research, Dublin, Ireland"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kotoulas", 
        "givenName": "Spyros", 
        "id": "sg:person.01070051744.59", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01070051744.59"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Smarter Cities Technology Centre, IBM Research, Dublin, Ireland", 
          "id": "http://www.grid.ac/institutes/grid.424816.d", 
          "name": [
            "Smarter Cities Technology Centre, IBM Research, Dublin, Ireland"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Wu", 
        "givenName": "Jiewen", 
        "id": "sg:person.07420566074.52", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07420566074.52"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2016-09-23", 
    "datePublishedReg": "2016-09-23", 
    "description": "We present a domain-agnostic system for Question Answering over multiple semi-structured and possibly linked datasets without the need of a training corpus. The system is motivated by an industry use-case where Enterprise Data needs to be combined with a large body of Open Data to fulfill information needs not satisfied by prescribed application data models. Our proposed Question Answering pipeline combines existing components with novel methods to perform, in turn, linguistic analysis of a query, named entity extraction, entity/graph search, fusion and ranking of possible answers. We evaluate QuerioDALI with two open-domain benchmarks and a biomedical one over Linked Open Data sources, and show that our system produces comparable results to systems that require training data and are domain-dependent. In addition, we analyze the current challenges and shortcomings.", 
    "editor": [
      {
        "familyName": "Groth", 
        "givenName": "Paul", 
        "type": "Person"
      }, 
      {
        "familyName": "Simperl", 
        "givenName": "Elena", 
        "type": "Person"
      }, 
      {
        "familyName": "Gray", 
        "givenName": "Alasdair", 
        "type": "Person"
      }, 
      {
        "familyName": "Sabou", 
        "givenName": "Marta", 
        "type": "Person"
      }, 
      {
        "familyName": "Kr\u00f6tzsch", 
        "givenName": "Markus", 
        "type": "Person"
      }, 
      {
        "familyName": "Lecue", 
        "givenName": "Freddy", 
        "type": "Person"
      }, 
      {
        "familyName": "Fl\u00f6ck", 
        "givenName": "Fabian", 
        "type": "Person"
      }, 
      {
        "familyName": "Gil", 
        "givenName": "Yolanda", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-319-46547-0_32", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-319-46546-3", 
        "978-3-319-46547-0"
      ], 
      "name": "The Semantic Web \u2013 ISWC 2016", 
      "type": "Book"
    }, 
    "keywords": [
      "Question Answering", 
      "Linked Open Data sources", 
      "Question Answering Pipelines", 
      "application data model", 
      "open data sources", 
      "graph search", 
      "knowledge graph", 
      "enterprise data", 
      "entity extraction", 
      "data model", 
      "open data", 
      "training data", 
      "training corpus", 
      "data sources", 
      "answering", 
      "novel method", 
      "queries", 
      "system", 
      "linguistic analysis", 
      "possible answers", 
      "datasets", 
      "graph", 
      "benchmarks", 
      "biomedical ones", 
      "corpus", 
      "current challenges", 
      "comparable results", 
      "pipeline", 
      "information", 
      "search", 
      "ranking", 
      "data", 
      "shortcomings", 
      "extraction", 
      "challenges", 
      "fusion", 
      "large body", 
      "answers", 
      "industry", 
      "method", 
      "need", 
      "model", 
      "one", 
      "components", 
      "results", 
      "source", 
      "analysis", 
      "dynamics", 
      "turn", 
      "addition", 
      "body", 
      "domain-agnostic system", 
      "prescribed application data models", 
      "Answering pipeline", 
      "entity/graph search", 
      "open-domain benchmarks", 
      "Linked Knowledge Graphs"
    ], 
    "name": "QuerioDALI: Question Answering Over Dynamic and Linked Knowledge Graphs", 
    "pagination": "363-382", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1084843894"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-319-46547-0_32"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-319-46547-0_32", 
      "https://app.dimensions.ai/details/publication/pub.1084843894"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2021-12-01T20:05", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20211201/entities/gbq_results/chapter/chapter_327.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-319-46547-0_32"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-46547-0_32'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-46547-0_32'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-46547-0_32'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-46547-0_32'


 

This table displays all metadata directly associated to this object as RDF triples.

173 TRIPLES      23 PREDICATES      82 URIs      75 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-319-46547-0_32 schema:about anzsrc-for:08
2 anzsrc-for:0806
3 schema:author Ndbb4118077ef42e9baf2cd7815ca080a
4 schema:datePublished 2016-09-23
5 schema:datePublishedReg 2016-09-23
6 schema:description We present a domain-agnostic system for Question Answering over multiple semi-structured and possibly linked datasets without the need of a training corpus. The system is motivated by an industry use-case where Enterprise Data needs to be combined with a large body of Open Data to fulfill information needs not satisfied by prescribed application data models. Our proposed Question Answering pipeline combines existing components with novel methods to perform, in turn, linguistic analysis of a query, named entity extraction, entity/graph search, fusion and ranking of possible answers. We evaluate QuerioDALI with two open-domain benchmarks and a biomedical one over Linked Open Data sources, and show that our system produces comparable results to systems that require training data and are domain-dependent. In addition, we analyze the current challenges and shortcomings.
7 schema:editor Nfe93e5b40a974473878778954fdf6b5b
8 schema:genre chapter
9 schema:inLanguage en
10 schema:isAccessibleForFree false
11 schema:isPartOf Na6f84d8244de4cd491e2ef30b5152cd7
12 schema:keywords Answering pipeline
13 Linked Knowledge Graphs
14 Linked Open Data sources
15 Question Answering
16 Question Answering Pipelines
17 addition
18 analysis
19 answering
20 answers
21 application data model
22 benchmarks
23 biomedical ones
24 body
25 challenges
26 comparable results
27 components
28 corpus
29 current challenges
30 data
31 data model
32 data sources
33 datasets
34 domain-agnostic system
35 dynamics
36 enterprise data
37 entity extraction
38 entity/graph search
39 extraction
40 fusion
41 graph
42 graph search
43 industry
44 information
45 knowledge graph
46 large body
47 linguistic analysis
48 method
49 model
50 need
51 novel method
52 one
53 open data
54 open data sources
55 open-domain benchmarks
56 pipeline
57 possible answers
58 prescribed application data models
59 queries
60 ranking
61 results
62 search
63 shortcomings
64 source
65 system
66 training corpus
67 training data
68 turn
69 schema:name QuerioDALI: Question Answering Over Dynamic and Linked Knowledge Graphs
70 schema:pagination 363-382
71 schema:productId N031c6a9f79dc49b4acaa6f19bdeb88f6
72 N31919b13799a4822af723967dafaaae6
73 schema:publisher Na9985f9b4967436999f67db66c779768
74 schema:sameAs https://app.dimensions.ai/details/publication/pub.1084843894
75 https://doi.org/10.1007/978-3-319-46547-0_32
76 schema:sdDatePublished 2021-12-01T20:05
77 schema:sdLicense https://scigraph.springernature.com/explorer/license/
78 schema:sdPublisher Neb3d0a6cb10542bf8ea7b6e818f198fa
79 schema:url https://doi.org/10.1007/978-3-319-46547-0_32
80 sgo:license sg:explorer/license/
81 sgo:sdDataset chapters
82 rdf:type schema:Chapter
83 N031c6a9f79dc49b4acaa6f19bdeb88f6 schema:name doi
84 schema:value 10.1007/978-3-319-46547-0_32
85 rdf:type schema:PropertyValue
86 N09184655aa7a493c8f201c47db86dbcd rdf:first Nea059c74d47541caa75f92067c35815c
87 rdf:rest N851caeaeeb2f40229e382d4cda94dd2a
88 N0c4ac7c021b34d59b97d3d875840cd49 schema:familyName Gray
89 schema:givenName Alasdair
90 rdf:type schema:Person
91 N28c57fd31bdf433590e826d855577575 rdf:first sg:person.010622151751.15
92 rdf:rest N714dd250b0834a4da7ad81b951a84853
93 N31919b13799a4822af723967dafaaae6 schema:name dimensions_id
94 schema:value pub.1084843894
95 rdf:type schema:PropertyValue
96 N36aecf34e11540d9b95950cdfda49b7c schema:familyName Gil
97 schema:givenName Yolanda
98 rdf:type schema:Person
99 N577b31d328b74a1faf3d2908aedf3623 rdf:first N36aecf34e11540d9b95950cdfda49b7c
100 rdf:rest rdf:nil
101 N714dd250b0834a4da7ad81b951a84853 rdf:first sg:person.01070051744.59
102 rdf:rest N9bc96910fd8a403db5da0653718d044a
103 N851caeaeeb2f40229e382d4cda94dd2a rdf:first N0c4ac7c021b34d59b97d3d875840cd49
104 rdf:rest Nbf1b9e6d51b445a3a277cb624ca28c0d
105 N999c8255f1a64fdda5e824d25c8f3c49 rdf:first Nff94da93525a49a59a0b8a2ddffe0aed
106 rdf:rest N577b31d328b74a1faf3d2908aedf3623
107 N9bc96910fd8a403db5da0653718d044a rdf:first sg:person.07420566074.52
108 rdf:rest rdf:nil
109 Na6f84d8244de4cd491e2ef30b5152cd7 schema:isbn 978-3-319-46546-3
110 978-3-319-46547-0
111 schema:name The Semantic Web – ISWC 2016
112 rdf:type schema:Book
113 Na877034698304945829d731011c15f45 rdf:first Nc998f5cbf55f4557bfbbcfcf5e17de40
114 rdf:rest N999c8255f1a64fdda5e824d25c8f3c49
115 Na9985f9b4967436999f67db66c779768 schema:name Springer Nature
116 rdf:type schema:Organisation
117 Nbf1b9e6d51b445a3a277cb624ca28c0d rdf:first Nc5c205e961244ae6808a8faec1ca496b
118 rdf:rest Ncda23fae19b2420cba06a93ef9049c28
119 Nc5c205e961244ae6808a8faec1ca496b schema:familyName Sabou
120 schema:givenName Marta
121 rdf:type schema:Person
122 Nc998f5cbf55f4557bfbbcfcf5e17de40 schema:familyName Lecue
123 schema:givenName Freddy
124 rdf:type schema:Person
125 Ncda23fae19b2420cba06a93ef9049c28 rdf:first Nd7d23c0d36d24fbf9413105b61ae510c
126 rdf:rest Na877034698304945829d731011c15f45
127 Nd7d23c0d36d24fbf9413105b61ae510c schema:familyName Krötzsch
128 schema:givenName Markus
129 rdf:type schema:Person
130 Ndbb4118077ef42e9baf2cd7815ca080a rdf:first sg:person.011057446515.94
131 rdf:rest N28c57fd31bdf433590e826d855577575
132 Ndecfd56464c24b1e9175836bb861d1fa schema:familyName Groth
133 schema:givenName Paul
134 rdf:type schema:Person
135 Nea059c74d47541caa75f92067c35815c schema:familyName Simperl
136 schema:givenName Elena
137 rdf:type schema:Person
138 Neb3d0a6cb10542bf8ea7b6e818f198fa schema:name Springer Nature - SN SciGraph project
139 rdf:type schema:Organization
140 Nfe93e5b40a974473878778954fdf6b5b rdf:first Ndecfd56464c24b1e9175836bb861d1fa
141 rdf:rest N09184655aa7a493c8f201c47db86dbcd
142 Nff94da93525a49a59a0b8a2ddffe0aed schema:familyName Flöck
143 schema:givenName Fabian
144 rdf:type schema:Person
145 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
146 schema:name Information and Computing Sciences
147 rdf:type schema:DefinedTerm
148 anzsrc-for:0806 schema:inDefinedTermSet anzsrc-for:
149 schema:name Information Systems
150 rdf:type schema:DefinedTerm
151 sg:person.010622151751.15 schema:affiliation grid-institutes:grid.424816.d
152 schema:familyName Tommasi
153 schema:givenName Pierpaolo
154 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010622151751.15
155 rdf:type schema:Person
156 sg:person.01070051744.59 schema:affiliation grid-institutes:grid.424816.d
157 schema:familyName Kotoulas
158 schema:givenName Spyros
159 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01070051744.59
160 rdf:type schema:Person
161 sg:person.011057446515.94 schema:affiliation grid-institutes:grid.424816.d
162 schema:familyName Lopez
163 schema:givenName Vanessa
164 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011057446515.94
165 rdf:type schema:Person
166 sg:person.07420566074.52 schema:affiliation grid-institutes:grid.424816.d
167 schema:familyName Wu
168 schema:givenName Jiewen
169 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07420566074.52
170 rdf:type schema:Person
171 grid-institutes:grid.424816.d schema:alternateName Smarter Cities Technology Centre, IBM Research, Dublin, Ireland
172 schema:name Smarter Cities Technology Centre, IBM Research, Dublin, Ireland
173 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...