Ontology type: schema:Chapter
2016-03-25
AUTHORSChristoph Lofi , Athiq Ahamed , Pratima Kulkarni , Ravi Thakkar
ABSTRACTEnabling semantically rich query paradigms is one of the core challenges of current information systems research. In this context, due to their importance and ubiquity in natural language, analogy queries are of particular interest. Current developments in natural language processing and machine learning resulted in some very promising algorithms relying on deep learning neural word embeddings which might contribute to finally realizing analogy queries. However, it is still quite unclear how well these algorithms work from a semantic point of view. One of the problems is that there is no clear consensus on the intended semantics of analogy queries. Furthermore, there are no suitable benchmark dataset available respecting the semantic properties of real-life analogies. Therefore, in this, paper, we discuss the challenges of benchmarking the semantics of analogy query algorithms with a special focus on neural embeddings. We also introduce the AGS analogy benchmark dataset which rectifies many weaknesses of established datasets. Finally, our experiments evaluating state-of-the-art algorithms underline the need for further research in this promising field. More... »
PAGES463-478
Database Systems for Advanced Applications
ISBN
978-3-319-32024-3
978-3-319-32025-0
http://scigraph.springernature.com/pub.10.1007/978-3-319-32025-0_29
DOIhttp://dx.doi.org/10.1007/978-3-319-32025-0_29
DIMENSIONShttps://app.dimensions.ai/details/publication/pub.1038291273
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/2008/0801",
"inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/",
"name": "Artificial Intelligence and Image Processing",
"type": "DefinedTerm"
}
],
"author": [
{
"affiliation": {
"alternateName": "Technische Universit\u00e4t Braunschweig, 38106, Brunswick, Germany",
"id": "http://www.grid.ac/institutes/grid.6738.a",
"name": [
"Technische Universit\u00e4t Braunschweig, 38106, Brunswick, Germany"
],
"type": "Organization"
},
"familyName": "Lofi",
"givenName": "Christoph",
"id": "sg:person.011355173745.44",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011355173745.44"
],
"type": "Person"
},
{
"affiliation": {
"alternateName": "Technische Universit\u00e4t Braunschweig, 38106, Brunswick, Germany",
"id": "http://www.grid.ac/institutes/grid.6738.a",
"name": [
"Technische Universit\u00e4t Braunschweig, 38106, Brunswick, Germany"
],
"type": "Organization"
},
"familyName": "Ahamed",
"givenName": "Athiq",
"type": "Person"
},
{
"affiliation": {
"alternateName": "Technische Universit\u00e4t Braunschweig, 38106, Brunswick, Germany",
"id": "http://www.grid.ac/institutes/grid.6738.a",
"name": [
"Technische Universit\u00e4t Braunschweig, 38106, Brunswick, Germany"
],
"type": "Organization"
},
"familyName": "Kulkarni",
"givenName": "Pratima",
"type": "Person"
},
{
"affiliation": {
"alternateName": "Technische Universit\u00e4t Braunschweig, 38106, Brunswick, Germany",
"id": "http://www.grid.ac/institutes/grid.6738.a",
"name": [
"Technische Universit\u00e4t Braunschweig, 38106, Brunswick, Germany"
],
"type": "Organization"
},
"familyName": "Thakkar",
"givenName": "Ravi",
"type": "Person"
}
],
"datePublished": "2016-03-25",
"datePublishedReg": "2016-03-25",
"description": "Enabling semantically rich query paradigms is one of the core challenges of current information systems research. In this context, due to their importance and ubiquity in natural language, analogy queries are of particular interest. Current developments in natural language processing and machine learning resulted in some very promising algorithms relying on deep learning neural word embeddings which might contribute to finally realizing analogy queries. However, it is still quite unclear how well these algorithms work from a semantic point of view. One of the problems is that there is no clear consensus on the intended semantics of analogy queries. Furthermore, there are no suitable benchmark dataset available respecting the semantic properties of real-life analogies. Therefore, in this, paper, we discuss the challenges of benchmarking the semantics of analogy query algorithms with a special focus on neural embeddings. We also introduce the AGS analogy benchmark dataset which rectifies many weaknesses of established datasets. Finally, our experiments evaluating state-of-the-art algorithms underline the need for further research in this promising field.",
"editor": [
{
"familyName": "Navathe",
"givenName": "Shamkant B.",
"type": "Person"
},
{
"familyName": "Wu",
"givenName": "Weili",
"type": "Person"
},
{
"familyName": "Shekhar",
"givenName": "Shashi",
"type": "Person"
},
{
"familyName": "Du",
"givenName": "Xiaoyong",
"type": "Person"
},
{
"familyName": "Wang",
"givenName": "X. Sean",
"type": "Person"
},
{
"familyName": "Xiong",
"givenName": "Hui",
"type": "Person"
}
],
"genre": "chapter",
"id": "sg:pub.10.1007/978-3-319-32025-0_29",
"inLanguage": "en",
"isAccessibleForFree": false,
"isPartOf": {
"isbn": [
"978-3-319-32024-3",
"978-3-319-32025-0"
],
"name": "Database Systems for Advanced Applications",
"type": "Book"
},
"keywords": [
"benchmark datasets",
"natural language processing",
"suitable benchmark datasets",
"information systems research",
"neural word embeddings",
"query paradigm",
"querying algorithm",
"query algorithm",
"semantic capabilities",
"machine learning",
"art algorithms",
"neural embeddings",
"natural language",
"language processing",
"word embeddings",
"promising algorithm",
"queries",
"systems research",
"semantic point",
"core challenge",
"algorithm",
"dataset",
"semantics",
"semantic properties",
"embedding",
"promising field",
"current developments",
"challenges",
"learning",
"language",
"paradigm",
"capability",
"processing",
"ubiquity",
"research",
"special focus",
"context",
"need",
"weakness",
"experiments",
"view",
"interest",
"point",
"field",
"focus",
"particular interest",
"further research",
"development",
"state",
"consensus",
"analogy",
"importance",
"properties",
"clear consensus",
"paper",
"problem"
],
"name": "Benchmarking Semantic Capabilities of Analogy Querying Algorithms",
"pagination": "463-478",
"productId": [
{
"name": "dimensions_id",
"type": "PropertyValue",
"value": [
"pub.1038291273"
]
},
{
"name": "doi",
"type": "PropertyValue",
"value": [
"10.1007/978-3-319-32025-0_29"
]
}
],
"publisher": {
"name": "Springer Nature",
"type": "Organisation"
},
"sameAs": [
"https://doi.org/10.1007/978-3-319-32025-0_29",
"https://app.dimensions.ai/details/publication/pub.1038291273"
],
"sdDataset": "chapters",
"sdDatePublished": "2022-06-01T22:30",
"sdLicense": "https://scigraph.springernature.com/explorer/license/",
"sdPublisher": {
"name": "Springer Nature - SN SciGraph project",
"type": "Organization"
},
"sdSource": "s3://com-springernature-scigraph/baseset/20220601/entities/gbq_results/chapter/chapter_26.jsonl",
"type": "Chapter",
"url": "https://doi.org/10.1007/978-3-319-32025-0_29"
}
]
Download the RDF metadata as: json-ld nt turtle xml License info
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.10.1007/978-3-319-32025-0_29'
N-Triples is a line-based linked data format ideal for batch operations.
curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-32025-0_29'
Turtle is a human-readable linked data format.
curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-32025-0_29'
RDF/XML is a standard XML format for linked data.
curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-32025-0_29'
This table displays all metadata directly associated to this object as RDF triples.
159 TRIPLES
23 PREDICATES
81 URIs
74 LITERALS
7 BLANK NODES