New Technique to Enhance the Performance of Spoken Dialogue Systems by Means of Implicit Recovery of ASR Errors View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2010

AUTHORS

Ramón López-Cózar , David Griol , José F. Quesada

ABSTRACT

This paper proposes a new technique to implicitly correct some ASR errors made by spoken dialogue systems, which is implemented at two levels: statistical and linguistic. The goal of the former level is to employ for the correction knowledge extracted from the analysis of a training corpus comprised of utterances and their corresponding ASR results. The outcome of the analysis is a set of syntactic-semantic models and a set of lexical models, which are optimally selected during the correction. The goal of the correction at the linguistic level is to repair errors not detected during the statistical level which affects the semantics of the sentences. Experiments carried out with a previously-developed spoken dialogue system for the fast food domain indicate that the technique allows enhancing word accuracy, spoken language understanding and task completion by 8.5%, 16.54% and 44.17% absolute, respectively. More... »

PAGES

96-109

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-642-16202-2_9

DOI

http://dx.doi.org/10.1007/978-3-642-16202-2_9

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1020750549


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/2008/20", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Language, Communication and Culture", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/2004", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Linguistics", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Dept. of Languages and Computer Systems, CITIC-UGR, University of Granada, Spain", 
          "id": "http://www.grid.ac/institutes/grid.4489.1", 
          "name": [
            "Dept. of Languages and Computer Systems, CITIC-UGR, University of Granada, Spain"
          ], 
          "type": "Organization"
        }, 
        "familyName": "L\u00f3pez-C\u00f3zar", 
        "givenName": "Ram\u00f3n", 
        "id": "sg:person.013113720067.02", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013113720067.02"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Dept. of Computer Science, Carlos III University of Madrid, Spain", 
          "id": "http://www.grid.ac/institutes/grid.7840.b", 
          "name": [
            "Dept. of Computer Science, Carlos III University of Madrid, Spain"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Griol", 
        "givenName": "David", 
        "id": "sg:person.013422741257.57", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013422741257.57"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Dept. of Artificial Intelligence and Computer Science, University of Seville, Spain", 
          "id": "http://www.grid.ac/institutes/grid.9224.d", 
          "name": [
            "Dept. of Artificial Intelligence and Computer Science, University of Seville, Spain"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Quesada", 
        "givenName": "Jos\u00e9 F.", 
        "id": "sg:person.011140123105.76", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011140123105.76"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2010", 
    "datePublishedReg": "2010-01-01", 
    "description": "This paper proposes a new technique to implicitly correct some ASR errors made by spoken dialogue systems, which is implemented at two levels: statistical and linguistic. The goal of the former level is to employ for the correction knowledge extracted from the analysis of a training corpus comprised of utterances and their corresponding ASR results. The outcome of the analysis is a set of syntactic-semantic models and a set of lexical models, which are optimally selected during the correction. The goal of the correction at the linguistic level is to repair errors not detected during the statistical level which affects the semantics of the sentences. Experiments carried out with a previously-developed spoken dialogue system for the fast food domain indicate that the technique allows enhancing word accuracy, spoken language understanding and task completion by 8.5%, 16.54% and 44.17% absolute, respectively.", 
    "editor": [
      {
        "familyName": "Lee", 
        "givenName": "Gary Geunbae", 
        "type": "Person"
      }, 
      {
        "familyName": "Mariani", 
        "givenName": "Joseph", 
        "type": "Person"
      }, 
      {
        "familyName": "Minker", 
        "givenName": "Wolfgang", 
        "type": "Person"
      }, 
      {
        "familyName": "Nakamura", 
        "givenName": "Satoshi", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-642-16202-2_9", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-642-16201-5", 
        "978-3-642-16202-2"
      ], 
      "name": "Spoken Dialogue Systems for Ambient Environments", 
      "type": "Book"
    }, 
    "keywords": [
      "spoken dialogue system", 
      "dialogue systems", 
      "ASR errors", 
      "linguistic levels", 
      "implicit recovery", 
      "language understanding", 
      "lexical model", 
      "training corpus", 
      "word accuracy", 
      "ASR results", 
      "corpus", 
      "utterances", 
      "sentences", 
      "semantics", 
      "food domain", 
      "task completion", 
      "understanding", 
      "knowledge", 
      "goal", 
      "former level", 
      "analysis", 
      "means", 
      "paper", 
      "set", 
      "domain", 
      "statistical level", 
      "levels", 
      "system", 
      "model", 
      "error", 
      "completion", 
      "performance", 
      "technique", 
      "results", 
      "outcomes", 
      "accuracy", 
      "correction", 
      "experiments", 
      "new technique", 
      "recovery", 
      "correction knowledge", 
      "corresponding ASR results", 
      "syntactic-semantic models", 
      "fast food domain"
    ], 
    "name": "New Technique to Enhance the Performance of Spoken Dialogue Systems by Means of Implicit Recovery of ASR Errors", 
    "pagination": "96-109", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1020750549"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-642-16202-2_9"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-642-16202-2_9", 
      "https://app.dimensions.ai/details/publication/pub.1020750549"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2021-12-01T20:01", 
    "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_250.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-642-16202-2_9"
  }
]
 

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.10.1007/978-3-642-16202-2_9'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-16202-2_9'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-16202-2_9'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-16202-2_9'


 

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

139 TRIPLES      23 PREDICATES      70 URIs      63 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-642-16202-2_9 schema:about anzsrc-for:20
2 anzsrc-for:2004
3 schema:author N6a63043424504f7997410e1d34d6d53f
4 schema:datePublished 2010
5 schema:datePublishedReg 2010-01-01
6 schema:description This paper proposes a new technique to implicitly correct some ASR errors made by spoken dialogue systems, which is implemented at two levels: statistical and linguistic. The goal of the former level is to employ for the correction knowledge extracted from the analysis of a training corpus comprised of utterances and their corresponding ASR results. The outcome of the analysis is a set of syntactic-semantic models and a set of lexical models, which are optimally selected during the correction. The goal of the correction at the linguistic level is to repair errors not detected during the statistical level which affects the semantics of the sentences. Experiments carried out with a previously-developed spoken dialogue system for the fast food domain indicate that the technique allows enhancing word accuracy, spoken language understanding and task completion by 8.5%, 16.54% and 44.17% absolute, respectively.
7 schema:editor N5aad0de5787445ac829837be75667bed
8 schema:genre chapter
9 schema:inLanguage en
10 schema:isAccessibleForFree false
11 schema:isPartOf Nacc9de56af06492da8ddd0d8948e490e
12 schema:keywords ASR errors
13 ASR results
14 accuracy
15 analysis
16 completion
17 corpus
18 correction
19 correction knowledge
20 corresponding ASR results
21 dialogue systems
22 domain
23 error
24 experiments
25 fast food domain
26 food domain
27 former level
28 goal
29 implicit recovery
30 knowledge
31 language understanding
32 levels
33 lexical model
34 linguistic levels
35 means
36 model
37 new technique
38 outcomes
39 paper
40 performance
41 recovery
42 results
43 semantics
44 sentences
45 set
46 spoken dialogue system
47 statistical level
48 syntactic-semantic models
49 system
50 task completion
51 technique
52 training corpus
53 understanding
54 utterances
55 word accuracy
56 schema:name New Technique to Enhance the Performance of Spoken Dialogue Systems by Means of Implicit Recovery of ASR Errors
57 schema:pagination 96-109
58 schema:productId N4a7893e9db18473695d1dd3cbde2332d
59 N7b0fff12bc7846f5ba8a6b11d9fd58db
60 schema:publisher N88cb93c82bb4407dac762339f80a5f70
61 schema:sameAs https://app.dimensions.ai/details/publication/pub.1020750549
62 https://doi.org/10.1007/978-3-642-16202-2_9
63 schema:sdDatePublished 2021-12-01T20:01
64 schema:sdLicense https://scigraph.springernature.com/explorer/license/
65 schema:sdPublisher N4041f09240064c4cb8586d6376ed04c5
66 schema:url https://doi.org/10.1007/978-3-642-16202-2_9
67 sgo:license sg:explorer/license/
68 sgo:sdDataset chapters
69 rdf:type schema:Chapter
70 N4041f09240064c4cb8586d6376ed04c5 schema:name Springer Nature - SN SciGraph project
71 rdf:type schema:Organization
72 N404850426aa34686a671035d822a7853 schema:familyName Nakamura
73 schema:givenName Satoshi
74 rdf:type schema:Person
75 N4a7893e9db18473695d1dd3cbde2332d schema:name doi
76 schema:value 10.1007/978-3-642-16202-2_9
77 rdf:type schema:PropertyValue
78 N55d515ec947744b4b4bef4a95ba66b22 schema:familyName Minker
79 schema:givenName Wolfgang
80 rdf:type schema:Person
81 N5aad0de5787445ac829837be75667bed rdf:first Nea9ee97ff8cb4070ac72087c004d8412
82 rdf:rest Ndd4a91218e74410cb810e7f6e298f029
83 N6a63043424504f7997410e1d34d6d53f rdf:first sg:person.013113720067.02
84 rdf:rest Nc20aa0b26efb4ad58e98df66675ef61d
85 N6c541483cf3440c2aa42818333e7f68c schema:familyName Mariani
86 schema:givenName Joseph
87 rdf:type schema:Person
88 N7b0fff12bc7846f5ba8a6b11d9fd58db schema:name dimensions_id
89 schema:value pub.1020750549
90 rdf:type schema:PropertyValue
91 N88cb93c82bb4407dac762339f80a5f70 schema:name Springer Nature
92 rdf:type schema:Organisation
93 N9cfbb9060f4840019e474f182c6710a8 rdf:first N404850426aa34686a671035d822a7853
94 rdf:rest rdf:nil
95 Nacc9de56af06492da8ddd0d8948e490e schema:isbn 978-3-642-16201-5
96 978-3-642-16202-2
97 schema:name Spoken Dialogue Systems for Ambient Environments
98 rdf:type schema:Book
99 Nb2e9c6d46ba34f1ebee66cbdcf5fb83a rdf:first sg:person.011140123105.76
100 rdf:rest rdf:nil
101 Nc20aa0b26efb4ad58e98df66675ef61d rdf:first sg:person.013422741257.57
102 rdf:rest Nb2e9c6d46ba34f1ebee66cbdcf5fb83a
103 Nc957ecd8f9b741c7b63b10152b79d2a1 rdf:first N55d515ec947744b4b4bef4a95ba66b22
104 rdf:rest N9cfbb9060f4840019e474f182c6710a8
105 Ndd4a91218e74410cb810e7f6e298f029 rdf:first N6c541483cf3440c2aa42818333e7f68c
106 rdf:rest Nc957ecd8f9b741c7b63b10152b79d2a1
107 Nea9ee97ff8cb4070ac72087c004d8412 schema:familyName Lee
108 schema:givenName Gary Geunbae
109 rdf:type schema:Person
110 anzsrc-for:20 schema:inDefinedTermSet anzsrc-for:
111 schema:name Language, Communication and Culture
112 rdf:type schema:DefinedTerm
113 anzsrc-for:2004 schema:inDefinedTermSet anzsrc-for:
114 schema:name Linguistics
115 rdf:type schema:DefinedTerm
116 sg:person.011140123105.76 schema:affiliation grid-institutes:grid.9224.d
117 schema:familyName Quesada
118 schema:givenName José F.
119 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011140123105.76
120 rdf:type schema:Person
121 sg:person.013113720067.02 schema:affiliation grid-institutes:grid.4489.1
122 schema:familyName López-Cózar
123 schema:givenName Ramón
124 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013113720067.02
125 rdf:type schema:Person
126 sg:person.013422741257.57 schema:affiliation grid-institutes:grid.7840.b
127 schema:familyName Griol
128 schema:givenName David
129 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013422741257.57
130 rdf:type schema:Person
131 grid-institutes:grid.4489.1 schema:alternateName Dept. of Languages and Computer Systems, CITIC-UGR, University of Granada, Spain
132 schema:name Dept. of Languages and Computer Systems, CITIC-UGR, University of Granada, Spain
133 rdf:type schema:Organization
134 grid-institutes:grid.7840.b schema:alternateName Dept. of Computer Science, Carlos III University of Madrid, Spain
135 schema:name Dept. of Computer Science, Carlos III University of Madrid, Spain
136 rdf:type schema:Organization
137 grid-institutes:grid.9224.d schema:alternateName Dept. of Artificial Intelligence and Computer Science, University of Seville, Spain
138 schema:name Dept. of Artificial Intelligence and Computer Science, University of Seville, Spain
139 rdf:type schema:Organization
 




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


...