Compositions of Tree-to-Tree Statistical Machine Translation Models View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2016-07-21

AUTHORS

Andreas Maletti

ABSTRACT

Compositions of well-known tree-to-tree translation models used in statistical machine translation are investigated. Synchronous context-free grammars are closed under composition in both the unweighted as well as the weighted case. In addition, it is demonstrated that there is a close connection between compositions of synchronous tree-substitution grammars and compositions of certain tree transducers because the intermediate trees can encode finite-state information. Utilizing these close ties, the composition closure of synchronous tree-substitution grammars is identified in the unweighted and weighted case. In particular, in the weighted case, these results build on a novel lifting strategy that will prove useful also in other setups. More... »

PAGES

293-305

Book

TITLE

Developments in Language Theory

ISBN

978-3-662-53131-0
978-3-662-53132-7

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-662-53132-7_24

DOI

http://dx.doi.org/10.1007/978-3-662-53132-7_24

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1014036301


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/2008/01", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Mathematical Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0104", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Statistics", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Institute for Natural Language Processing, Universit\u00e4t Stuttgart, Pfaffenwaldring 5b, 70569, Stuttgart, Germany", 
          "id": "http://www.grid.ac/institutes/grid.5719.a", 
          "name": [
            "Institute for Natural Language Processing, Universit\u00e4t Stuttgart, Pfaffenwaldring 5b, 70569, Stuttgart, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Maletti", 
        "givenName": "Andreas", 
        "id": "sg:person.016645332751.01", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016645332751.01"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2016-07-21", 
    "datePublishedReg": "2016-07-21", 
    "description": "Compositions of well-known tree-to-tree translation models used in statistical machine translation are investigated. Synchronous context-free grammars are closed under composition in both the unweighted as well as the weighted case. In addition, it is demonstrated that there is a close connection between compositions of synchronous tree-substitution grammars and compositions of certain tree transducers because the intermediate trees can encode finite-state information. Utilizing these close ties, the composition closure of synchronous tree-substitution grammars is identified in the unweighted and weighted case. In particular, in the weighted case, these results build on a novel lifting strategy that will prove useful also in other setups.", 
    "editor": [
      {
        "familyName": "Brlek", 
        "givenName": "Sre\u010dko", 
        "type": "Person"
      }, 
      {
        "familyName": "Reutenauer", 
        "givenName": "Christophe", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-662-53132-7_24", 
    "inLanguage": "en", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-662-53131-0", 
        "978-3-662-53132-7"
      ], 
      "name": "Developments in Language Theory", 
      "type": "Book"
    }, 
    "keywords": [
      "weighted case", 
      "statistical machine translation models", 
      "translation model", 
      "close connection", 
      "model", 
      "statistical machine translation", 
      "context-free grammars", 
      "machine translation model", 
      "cases", 
      "lifting strategy", 
      "trees", 
      "connection", 
      "close ties", 
      "setup", 
      "composition", 
      "machine translation", 
      "grammar", 
      "tree transducers", 
      "information", 
      "closure", 
      "results", 
      "strategies", 
      "translation", 
      "addition", 
      "ties", 
      "composition of trees", 
      "transducer", 
      "intermediate trees", 
      "tree translation models", 
      "synchronous context-free grammar", 
      "synchronous tree-substitution grammars", 
      "tree-substitution grammars", 
      "certain tree transducers", 
      "finite-state information", 
      "composition closure", 
      "novel lifting strategy", 
      "Tree Statistical Machine Translation Models"
    ], 
    "name": "Compositions of Tree-to-Tree Statistical Machine Translation Models", 
    "pagination": "293-305", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1014036301"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-662-53132-7_24"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-662-53132-7_24", 
      "https://app.dimensions.ai/details/publication/pub.1014036301"
    ], 
    "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_322.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-662-53132-7_24"
  }
]
 

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.10.1007/978-3-662-53132-7_24'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-662-53132-7_24'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-662-53132-7_24'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-662-53132-7_24'


 

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

102 TRIPLES      23 PREDICATES      62 URIs      55 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-662-53132-7_24 schema:about anzsrc-for:01
2 anzsrc-for:0104
3 schema:author N904e9d7c43fa4fb2adc2906d0ac0b256
4 schema:datePublished 2016-07-21
5 schema:datePublishedReg 2016-07-21
6 schema:description Compositions of well-known tree-to-tree translation models used in statistical machine translation are investigated. Synchronous context-free grammars are closed under composition in both the unweighted as well as the weighted case. In addition, it is demonstrated that there is a close connection between compositions of synchronous tree-substitution grammars and compositions of certain tree transducers because the intermediate trees can encode finite-state information. Utilizing these close ties, the composition closure of synchronous tree-substitution grammars is identified in the unweighted and weighted case. In particular, in the weighted case, these results build on a novel lifting strategy that will prove useful also in other setups.
7 schema:editor Nd60d51659d784a47996d36fbd88b8b47
8 schema:genre chapter
9 schema:inLanguage en
10 schema:isAccessibleForFree false
11 schema:isPartOf N5d19cc399ede40f29e8b58001469bf59
12 schema:keywords Tree Statistical Machine Translation Models
13 addition
14 cases
15 certain tree transducers
16 close connection
17 close ties
18 closure
19 composition
20 composition closure
21 composition of trees
22 connection
23 context-free grammars
24 finite-state information
25 grammar
26 information
27 intermediate trees
28 lifting strategy
29 machine translation
30 machine translation model
31 model
32 novel lifting strategy
33 results
34 setup
35 statistical machine translation
36 statistical machine translation models
37 strategies
38 synchronous context-free grammar
39 synchronous tree-substitution grammars
40 ties
41 transducer
42 translation
43 translation model
44 tree transducers
45 tree translation models
46 tree-substitution grammars
47 trees
48 weighted case
49 schema:name Compositions of Tree-to-Tree Statistical Machine Translation Models
50 schema:pagination 293-305
51 schema:productId N72c921cfe8b74d8ab4f71c52dc8a3a24
52 N7fabc8b5be0b44a5b03fb85d2c5e9ed3
53 schema:publisher N0e8edf6eac694947aeacba79504c445e
54 schema:sameAs https://app.dimensions.ai/details/publication/pub.1014036301
55 https://doi.org/10.1007/978-3-662-53132-7_24
56 schema:sdDatePublished 2021-12-01T20:05
57 schema:sdLicense https://scigraph.springernature.com/explorer/license/
58 schema:sdPublisher N121f2dd00258413eb0e3fdc20d139780
59 schema:url https://doi.org/10.1007/978-3-662-53132-7_24
60 sgo:license sg:explorer/license/
61 sgo:sdDataset chapters
62 rdf:type schema:Chapter
63 N0e8edf6eac694947aeacba79504c445e schema:name Springer Nature
64 rdf:type schema:Organisation
65 N121f2dd00258413eb0e3fdc20d139780 schema:name Springer Nature - SN SciGraph project
66 rdf:type schema:Organization
67 N4a8a40098b024f49923de22e1a63a831 schema:familyName Brlek
68 schema:givenName Srečko
69 rdf:type schema:Person
70 N5d19cc399ede40f29e8b58001469bf59 schema:isbn 978-3-662-53131-0
71 978-3-662-53132-7
72 schema:name Developments in Language Theory
73 rdf:type schema:Book
74 N72c921cfe8b74d8ab4f71c52dc8a3a24 schema:name dimensions_id
75 schema:value pub.1014036301
76 rdf:type schema:PropertyValue
77 N7fabc8b5be0b44a5b03fb85d2c5e9ed3 schema:name doi
78 schema:value 10.1007/978-3-662-53132-7_24
79 rdf:type schema:PropertyValue
80 N8028c4fc02854f5cb287d9ac4878896f rdf:first Nb7af0e62ffc343cfbfa99550f50e66d3
81 rdf:rest rdf:nil
82 N904e9d7c43fa4fb2adc2906d0ac0b256 rdf:first sg:person.016645332751.01
83 rdf:rest rdf:nil
84 Nb7af0e62ffc343cfbfa99550f50e66d3 schema:familyName Reutenauer
85 schema:givenName Christophe
86 rdf:type schema:Person
87 Nd60d51659d784a47996d36fbd88b8b47 rdf:first N4a8a40098b024f49923de22e1a63a831
88 rdf:rest N8028c4fc02854f5cb287d9ac4878896f
89 anzsrc-for:01 schema:inDefinedTermSet anzsrc-for:
90 schema:name Mathematical Sciences
91 rdf:type schema:DefinedTerm
92 anzsrc-for:0104 schema:inDefinedTermSet anzsrc-for:
93 schema:name Statistics
94 rdf:type schema:DefinedTerm
95 sg:person.016645332751.01 schema:affiliation grid-institutes:grid.5719.a
96 schema:familyName Maletti
97 schema:givenName Andreas
98 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016645332751.01
99 rdf:type schema:Person
100 grid-institutes:grid.5719.a schema:alternateName Institute for Natural Language Processing, Universität Stuttgart, Pfaffenwaldring 5b, 70569, Stuttgart, Germany
101 schema:name Institute for Natural Language Processing, Universität Stuttgart, Pfaffenwaldring 5b, 70569, Stuttgart, Germany
102 rdf:type schema:Organization
 




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


...