RI: Large: Collaborative Research: Richer Representations for Machine Translation View Homepage


Ontology type: schema:MonetaryGrant     


Grant Info

YEARS

2009-2015

FUNDING AMOUNT

559847 USD

ABSTRACT

Research in machine translation of human languages has made substantial progress recently, and surface patterns gleaned automatically from online bilingual texts work remarkably well for some language pairs. However, for many language pairs, the output of even the best systems is garbled, ungrammatical, and difficult to interpret. Chinese-to-English systems need particular improvement, despite the importance of this language pair, while English-to-Chinese translation, equally important for communication between individuals, is rarely studied. This project develops methods for automatically learning correspondences between Chinese and English at a semantic rather than surface level, allowing machine translation to benefit from recent work in semantic analysis of text and natural language generation. One part of this work determines what types of semantic analysis of source language sentences can best inform a translation system, focusing on analyzing dropped arguments, co-reference links, and discourse relations between clauses. These linguistic phenomena must generally be made more explicit when translating from Chinese to English. A second part of the work integrates natural language generation into statistical machine translation, leveraging generation technology to determine sentence boundaries, ordering of constituents, and production of function words that translation systems tend to get wrong. A third part develops and compares algorithms for training and decoding machine translation models defined on semantic representations. All of this research exploits newly-developed linguistic resources for semantic analysis of both Chinese and English. The ultimate benefits of improved machine translation technology are easier access to information and easier communication between individuals. This in turn leads to increased opportunities for trade, as well as better understanding between cultures. This project's systems for both Chinese-to-English and English-to-Chinese are developed with the expectation that the approaches will be applied to other language pairs in the future. More... »

URL

http://www.nsf.gov/awardsearch/showAward?AWD_ID=0910532&HistoricalAwards=false

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/2008/2208", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/2220", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "type": "DefinedTerm"
      }
    ], 
    "amount": {
      "currency": "USD", 
      "type": "MonetaryAmount", 
      "value": "559847"
    }, 
    "description": "Research in machine translation of human languages has made substantial progress recently, and surface patterns gleaned automatically from online bilingual texts work remarkably well for some language pairs. However, for many language pairs, the output of even the best systems is garbled, ungrammatical, and difficult to interpret. Chinese-to-English systems need particular improvement, despite the importance of this language pair, while English-to-Chinese translation, equally important for communication between individuals, is rarely studied. This project develops methods for automatically learning correspondences between Chinese and English at a semantic rather than surface level, allowing machine translation to benefit from recent work in semantic analysis of text and natural language generation. One part of this work determines what types of semantic analysis of source language sentences can best inform a translation system, focusing on analyzing dropped arguments, co-reference links, and discourse relations between clauses. These linguistic phenomena must generally be made more explicit when translating from Chinese to English. A second part of the work integrates natural language generation into statistical machine translation, leveraging generation technology to determine sentence boundaries, ordering of constituents, and production of function words that translation systems tend to get wrong. A third part develops and compares algorithms for training and decoding machine translation models defined on semantic representations. All of this research exploits newly-developed linguistic resources for semantic analysis of both Chinese and English. The ultimate benefits of improved machine translation technology are easier access to information and easier communication between individuals. This in turn leads to increased opportunities for trade, as well as better understanding between cultures. This project's systems for both Chinese-to-English and English-to-Chinese are developed with the expectation that the approaches will be applied to other language pairs in the future.", 
    "endDate": "2015-08-31T00:00:00Z", 
    "funder": {
      "id": "https://www.grid.ac/institutes/grid.457785.c", 
      "type": "Organization"
    }, 
    "id": "sg:grant.3101276", 
    "identifier": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "3101276"
        ]
      }, 
      {
        "name": "nsf_id", 
        "type": "PropertyValue", 
        "value": [
          "0910532"
        ]
      }
    ], 
    "inLanguage": [
      "en"
    ], 
    "keywords": [
      "English", 
      "Chinese", 
      "second part", 
      "communication", 
      "source language sentence", 
      "Large", 
      "surface level", 
      "linguistic phenomena", 
      "constituents", 
      "substantial progress", 
      "future", 
      "METHODS", 
      "sentence boundaries", 
      "discourse relations", 
      "type", 
      "text", 
      "English system", 
      "algorithms", 
      "statistical machine translation", 
      "training", 
      "third part", 
      "surface patterns", 
      "Chinese translation", 
      "output", 
      "approach", 
      "trade", 
      "project system", 
      "online bilingual texts work", 
      "correspondence", 
      "translation system", 
      "generation technologies", 
      "research", 
      "importance", 
      "linguistic resources", 
      "semantic representation", 
      "natural language generation", 
      "best system", 
      "clauses", 
      "machine translation models", 
      "semantic analysis", 
      "function words", 
      "easy access", 
      "human language", 
      "reference links", 
      "easy communication", 
      "Richer Representations", 
      "culture", 
      "other language pairs", 
      "part", 
      "work", 
      "production", 
      "turn", 
      "particular improvement", 
      "argument", 
      "recent work", 
      "information", 
      "expectations", 
      "better understanding", 
      "project", 
      "machine translation technology", 
      "language pairs", 
      "opportunity", 
      "individuals", 
      "ultimate benefit", 
      "machine translation", 
      "many language pairs", 
      "collaborative research", 
      "RI"
    ], 
    "name": "RI: Large: Collaborative Research: Richer Representations for Machine Translation", 
    "recipient": [
      {
        "id": "https://www.grid.ac/institutes/grid.253264.4", 
        "type": "Organization"
      }, 
      {
        "affiliation": {
          "id": "https://www.grid.ac/institutes/grid.253264.4", 
          "name": "Brandeis University", 
          "type": "Organization"
        }, 
        "familyName": "Xue", 
        "givenName": "Nianwen", 
        "id": "sg:person.012613717520.24", 
        "type": "Person"
      }, 
      {
        "member": "sg:person.012613717520.24", 
        "roleName": "PI", 
        "type": "Role"
      }
    ], 
    "sameAs": [
      "https://app.dimensions.ai/details/grant/grant.3101276"
    ], 
    "sdDataset": "grants", 
    "sdDatePublished": "2019-03-07T12:33", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com.uberresearch.data.processor/core_data/20181219_192338/projects/base/nsf_projects_4.xml.gz", 
    "startDate": "2009-09-01T00:00:00Z", 
    "type": "MonetaryGrant", 
    "url": "http://www.nsf.gov/awardsearch/showAward?AWD_ID=0910532&HistoricalAwards=false"
  }
]
 

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/grant.3101276'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/grant.3101276'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/grant.3101276'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/grant.3101276'


 

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

115 TRIPLES      19 PREDICATES      91 URIs      82 LITERALS      5 BLANK NODES

Subject Predicate Object
1 sg:grant.3101276 schema:about anzsrc-for:2208
2 anzsrc-for:2220
3 schema:amount N427ffa91938d40f7b6f74fc6a42d9af8
4 schema:description Research in machine translation of human languages has made substantial progress recently, and surface patterns gleaned automatically from online bilingual texts work remarkably well for some language pairs. However, for many language pairs, the output of even the best systems is garbled, ungrammatical, and difficult to interpret. Chinese-to-English systems need particular improvement, despite the importance of this language pair, while English-to-Chinese translation, equally important for communication between individuals, is rarely studied. This project develops methods for automatically learning correspondences between Chinese and English at a semantic rather than surface level, allowing machine translation to benefit from recent work in semantic analysis of text and natural language generation. One part of this work determines what types of semantic analysis of source language sentences can best inform a translation system, focusing on analyzing dropped arguments, co-reference links, and discourse relations between clauses. These linguistic phenomena must generally be made more explicit when translating from Chinese to English. A second part of the work integrates natural language generation into statistical machine translation, leveraging generation technology to determine sentence boundaries, ordering of constituents, and production of function words that translation systems tend to get wrong. A third part develops and compares algorithms for training and decoding machine translation models defined on semantic representations. All of this research exploits newly-developed linguistic resources for semantic analysis of both Chinese and English. The ultimate benefits of improved machine translation technology are easier access to information and easier communication between individuals. This in turn leads to increased opportunities for trade, as well as better understanding between cultures. This project's systems for both Chinese-to-English and English-to-Chinese are developed with the expectation that the approaches will be applied to other language pairs in the future.
5 schema:endDate 2015-08-31T00:00:00Z
6 schema:funder https://www.grid.ac/institutes/grid.457785.c
7 schema:identifier Nd2c377cbb8c844e0910f04f56ab4bc12
8 Nf3c68322f57c4a68999898140419a6a2
9 schema:inLanguage en
10 schema:keywords Chinese
11 Chinese translation
12 English
13 English system
14 Large
15 METHODS
16 RI
17 Richer Representations
18 algorithms
19 approach
20 argument
21 best system
22 better understanding
23 clauses
24 collaborative research
25 communication
26 constituents
27 correspondence
28 culture
29 discourse relations
30 easy access
31 easy communication
32 expectations
33 function words
34 future
35 generation technologies
36 human language
37 importance
38 individuals
39 information
40 language pairs
41 linguistic phenomena
42 linguistic resources
43 machine translation
44 machine translation models
45 machine translation technology
46 many language pairs
47 natural language generation
48 online bilingual texts work
49 opportunity
50 other language pairs
51 output
52 part
53 particular improvement
54 production
55 project
56 project system
57 recent work
58 reference links
59 research
60 second part
61 semantic analysis
62 semantic representation
63 sentence boundaries
64 source language sentence
65 statistical machine translation
66 substantial progress
67 surface level
68 surface patterns
69 text
70 third part
71 trade
72 training
73 translation system
74 turn
75 type
76 ultimate benefit
77 work
78 schema:name RI: Large: Collaborative Research: Richer Representations for Machine Translation
79 schema:recipient N83b23a5c0490492a92d511a96a271d7a
80 sg:person.012613717520.24
81 https://www.grid.ac/institutes/grid.253264.4
82 schema:sameAs https://app.dimensions.ai/details/grant/grant.3101276
83 schema:sdDatePublished 2019-03-07T12:33
84 schema:sdLicense https://scigraph.springernature.com/explorer/license/
85 schema:sdPublisher N14f783f24c094fd294e826665347f440
86 schema:startDate 2009-09-01T00:00:00Z
87 schema:url http://www.nsf.gov/awardsearch/showAward?AWD_ID=0910532&HistoricalAwards=false
88 sgo:license sg:explorer/license/
89 sgo:sdDataset grants
90 rdf:type schema:MonetaryGrant
91 N14f783f24c094fd294e826665347f440 schema:name Springer Nature - SN SciGraph project
92 rdf:type schema:Organization
93 N427ffa91938d40f7b6f74fc6a42d9af8 schema:currency USD
94 schema:value 559847
95 rdf:type schema:MonetaryAmount
96 N83b23a5c0490492a92d511a96a271d7a schema:member sg:person.012613717520.24
97 schema:roleName PI
98 rdf:type schema:Role
99 Nd2c377cbb8c844e0910f04f56ab4bc12 schema:name dimensions_id
100 schema:value 3101276
101 rdf:type schema:PropertyValue
102 Nf3c68322f57c4a68999898140419a6a2 schema:name nsf_id
103 schema:value 0910532
104 rdf:type schema:PropertyValue
105 anzsrc-for:2208 schema:inDefinedTermSet anzsrc-for:
106 rdf:type schema:DefinedTerm
107 anzsrc-for:2220 schema:inDefinedTermSet anzsrc-for:
108 rdf:type schema:DefinedTerm
109 sg:person.012613717520.24 schema:affiliation https://www.grid.ac/institutes/grid.253264.4
110 schema:familyName Xue
111 schema:givenName Nianwen
112 rdf:type schema:Person
113 https://www.grid.ac/institutes/grid.253264.4 schema:name Brandeis University
114 rdf:type schema:Organization
115 https://www.grid.ac/institutes/grid.457785.c schema:Organization
 




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


...