Translation Word Order Information Output Device, Translation Word Order Information Output Method, And Recording Medium


Ontology type: sgo:Patent     


Patent Info

DATE

N/A

AUTHORS

後藤 功雄

ABSTRACT

[Problem] It has hitherto been difficult to correctly determine the word order of a translation in statistical machine translation. [Solution] A translation word order information output device is provided with: a sentence storage unit capable of storing an original language sentence; a weight vector storage unit capable of storing a weight vector; an acceptance unit which accepts the present term position of a present term that is a term to be translated at present; a candidate acquisition unit which acquires, from the original language sentence, the present term position, and one or more next term position candidates that become candidates for translation after the present term; a vector acquisition unit which acquires a vector having two or more elements using the present term, a next term candidate, and the original language sentence; a probability information acquisition unit which, using the vector and the weight vector, acquires, in each of the one or more next term position candidates, probability information relating to the probability that a term in each of the one or more next term position candidates is a next term to be translated after the present term; and an output unit which outputs the probability information. The translation word order information output device makes it possible to correctly determine a term to be translated next in a state where a term translated at present is known in the original language sentence. More... »

Related SciGraph Publications

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/2008/3616", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "name": "\u5f8c\u85e4 \u529f\u96c4", 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1007/bf01589116", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1022481421", 
          "https://doi.org/10.1007/bf01589116"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "description": "

[Problem] It has hitherto been difficult to correctly determine the word order of a translation in statistical machine translation.\n[Solution] A translation word order information output device is provided with: a sentence storage unit capable of storing an original language sentence; a weight vector storage unit capable of storing a weight vector; an acceptance unit which accepts the present term position of a present term that is a term to be translated at present; a candidate acquisition unit which acquires, from the original language sentence, the present term position, and one or more next term position candidates that become candidates for translation after the present term; a vector acquisition unit which acquires a vector having two or more elements using the present term, a next term candidate, and the original language sentence; a probability information acquisition unit which, using the vector and the weight vector, acquires, in each of the one or more next term position candidates, probability information relating to the probability that a term in each of the one or more next term position candidates is a next term to be translated after the present term; and an output unit which outputs the probability information. The translation word order information output device makes it possible to correctly determine a term to be translated next in a state where a term translated at present is known in the original language sentence.

", "id": "sg:patent.WO-2014192598-A1", "keywords": [ "output device", "word order", "recording medium", "translation", "statistical machine translation", "solution", "storage unit", "language", "weight", "acceptance", "accepts", "acquisition", "vector", "element", "information acquisition", "probability", "output", "state" ], "name": "TRANSLATION WORD ORDER INFORMATION OUTPUT DEVICE, TRANSLATION WORD ORDER INFORMATION OUTPUT METHOD, AND RECORDING MEDIUM", "recipient": [ { "id": "https://www.grid.ac/institutes/grid.28312.3a", "type": "Organization" } ], "sameAs": [ "https://app.dimensions.ai/details/patent/WO-2014192598-A1" ], "sdDataset": "patents", "sdDatePublished": "2019-03-07T15:36", "sdLicense": "https://scigraph.springernature.com/explorer/license/", "sdPublisher": { "name": "Springer Nature - SN SciGraph project", "type": "Organization" }, "sdSource": "s3://com.uberresearch.data.dev.patents-pipeline/full_run_10/sn-export/5eb3e5a348d7f117b22cc85fb0b02730/0000100128-0000348334/json_export_c3e5ed81.jsonl", "type": "Patent" } ]
 

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/patent.WO-2014192598-A1'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/patent.WO-2014192598-A1'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/patent.WO-2014192598-A1'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/patent.WO-2014192598-A1'


 

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

43 TRIPLES      14 PREDICATES      32 URIs      25 LITERALS      2 BLANK NODES

Subject Predicate Object
1 sg:patent.WO-2014192598-A1 schema:about anzsrc-for:3616
2 schema:author N4416f32f834540b2bd670b6d3cfffa7c
3 schema:citation sg:pub.10.1007/bf01589116
4 schema:description <p>[Problem] It has hitherto been difficult to correctly determine the word order of a translation in statistical machine translation. [Solution] A translation word order information output device is provided with: a sentence storage unit capable of storing an original language sentence; a weight vector storage unit capable of storing a weight vector; an acceptance unit which accepts the present term position of a present term that is a term to be translated at present; a candidate acquisition unit which acquires, from the original language sentence, the present term position, and one or more next term position candidates that become candidates for translation after the present term; a vector acquisition unit which acquires a vector having two or more elements using the present term, a next term candidate, and the original language sentence; a probability information acquisition unit which, using the vector and the weight vector, acquires, in each of the one or more next term position candidates, probability information relating to the probability that a term in each of the one or more next term position candidates is a next term to be translated after the present term; and an output unit which outputs the probability information. The translation word order information output device makes it possible to correctly determine a term to be translated next in a state where a term translated at present is known in the original language sentence.</p>
5 schema:keywords acceptance
6 accepts
7 acquisition
8 element
9 information acquisition
10 language
11 output
12 output device
13 probability
14 recording medium
15 solution
16 state
17 statistical machine translation
18 storage unit
19 translation
20 vector
21 weight
22 word order
23 schema:name TRANSLATION WORD ORDER INFORMATION OUTPUT DEVICE, TRANSLATION WORD ORDER INFORMATION OUTPUT METHOD, AND RECORDING MEDIUM
24 schema:recipient https://www.grid.ac/institutes/grid.28312.3a
25 schema:sameAs https://app.dimensions.ai/details/patent/WO-2014192598-A1
26 schema:sdDatePublished 2019-03-07T15:36
27 schema:sdLicense https://scigraph.springernature.com/explorer/license/
28 schema:sdPublisher N704ac289f0f34d71b4af8b8bc044b138
29 sgo:license sg:explorer/license/
30 sgo:sdDataset patents
31 rdf:type sgo:Patent
32 N2f7ac28114f54573a75e52ff8218e53d schema:name 後藤 功雄
33 rdf:type schema:Person
34 N4416f32f834540b2bd670b6d3cfffa7c rdf:first N2f7ac28114f54573a75e52ff8218e53d
35 rdf:rest rdf:nil
36 N704ac289f0f34d71b4af8b8bc044b138 schema:name Springer Nature - SN SciGraph project
37 rdf:type schema:Organization
38 anzsrc-for:3616 schema:inDefinedTermSet anzsrc-for:
39 rdf:type schema:DefinedTerm
40 sg:pub.10.1007/bf01589116 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022481421
41 https://doi.org/10.1007/bf01589116
42 rdf:type schema:CreativeWork
43 https://www.grid.ac/institutes/grid.28312.3a schema:Organization
 




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


...