Answering Natural Language Questions via Phrasal Semantic Parsing View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2014

AUTHORS

Kun Xu , Sheng Zhang , Yansong Feng , Dongyan Zhao

ABSTRACT

Understanding natural language questions and converting them into structured queries have been considered as a crucial way to help users access large scale structured knowledge bases. However, the task usually involves two main challenges: recognizing users’ query intention and mapping the involved semantic items against a given knowledge base (KB). In this paper, we propose an efficient pipeline framework to model a user’s query intention as a phrase level dependency DAG which is then instantiated regarding a specific KB to construct the final structured query. Our model benefits from the efficiency of linear structured prediction models and the separation of KB-independent and KB-related modelings. We evaluate our model on two datasets, and the experimental results showed that our method outperforms the state-of-the-art methods on the Free917 dataset, and, with limited training data from Free917, our model can smoothly adapt to new challenging dataset, WebQuestion, without extra training efforts while maintaining promising performances. More... »

PAGES

333-344

References to SciGraph publications

  • 2011. Pythia: Compositional Meaning Construction for Ontology-Based Question Answering on the Semantic Web in NATURAL LANGUAGE PROCESSING AND INFORMATION SYSTEMS
  • 2007. DBpedia: A Nucleus for a Web of Open Data in THE SEMANTIC WEB
  • 2013. Multilingual Question Answering over Linked Data (QALD-3): Lab Overview in INFORMATION ACCESS EVALUATION. MULTILINGUALITY, MULTIMODALITY, AND VISUALIZATION
  • Book

    TITLE

    Natural Language Processing and Chinese Computing

    ISBN

    978-3-662-45923-2
    978-3-662-45924-9

    Author Affiliations

    Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/978-3-662-45924-9_30

    DOI

    http://dx.doi.org/10.1007/978-3-662-45924-9_30

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1042493657


    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/2008/0801", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Artificial Intelligence and Image Processing", 
            "type": "DefinedTerm"
          }, 
          {
            "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"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Peking University", 
              "id": "https://www.grid.ac/institutes/grid.11135.37", 
              "name": [
                "Peking University, Beijing, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Xu", 
            "givenName": "Kun", 
            "id": "sg:person.010500262013.31", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010500262013.31"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Peking University", 
              "id": "https://www.grid.ac/institutes/grid.11135.37", 
              "name": [
                "Peking University, Beijing, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Zhang", 
            "givenName": "Sheng", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Peking University", 
              "id": "https://www.grid.ac/institutes/grid.11135.37", 
              "name": [
                "Peking University, Beijing, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Feng", 
            "givenName": "Yansong", 
            "id": "sg:person.010630657066.08", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010630657066.08"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Peking University", 
              "id": "https://www.grid.ac/institutes/grid.11135.37", 
              "name": [
                "Peking University, Beijing, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Zhao", 
            "givenName": "Dongyan", 
            "id": "sg:person.016004203227.20", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016004203227.20"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/978-3-642-40802-1_30", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1018433437", 
              "https://doi.org/10.1007/978-3-642-40802-1_30"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/2187836.2187923", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1019604077"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-76298-0_52", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1028565626", 
              "https://doi.org/10.1007/978-3-540-76298-0_52"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-76298-0_52", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1028565626", 
              "https://doi.org/10.1007/978-3-540-76298-0_52"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.jal.2005.12.006", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1038280045"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-22327-3_15", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1046687882", 
              "https://doi.org/10.1007/978-3-642-22327-3_15"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-22327-3_15", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1046687882", 
              "https://doi.org/10.1007/978-3-642-22327-3_15"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.3115/v1/p14-1090", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099110676"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.3115/v1/p14-1090", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099110676"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.3115/v1/p14-1133", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099110721"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.3115/v1/p14-1133", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099110721"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.3115/1118693.1118694", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099201575"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.3115/1118693.1118694", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099201575"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.3115/1599081.1599176", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099206013"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.3115/1218955.1218970", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099221196"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.3115/1218955.1218970", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099221196"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2014", 
        "datePublishedReg": "2014-01-01", 
        "description": "Understanding natural language questions and converting them into structured queries have been considered as a crucial way to help users access large scale structured knowledge bases. However, the task usually involves two main challenges: recognizing users\u2019 query intention and mapping the involved semantic items against a given knowledge base (KB). In this paper, we propose an efficient pipeline framework to model a user\u2019s query intention as a phrase level dependency DAG which is then instantiated regarding a specific KB to construct the final structured query. Our model benefits from the efficiency of linear structured prediction models and the separation of KB-independent and KB-related modelings. We evaluate our model on two datasets, and the experimental results showed that our method outperforms the state-of-the-art methods on the Free917 dataset, and, with limited training data from Free917, our model can smoothly adapt to new challenging dataset, WebQuestion, without extra training efforts while maintaining promising performances.", 
        "editor": [
          {
            "familyName": "Zong", 
            "givenName": "Chengqing", 
            "type": "Person"
          }, 
          {
            "familyName": "Nie", 
            "givenName": "Jian-Yun", 
            "type": "Person"
          }, 
          {
            "familyName": "Zhao", 
            "givenName": "Dongyan", 
            "type": "Person"
          }, 
          {
            "familyName": "Feng", 
            "givenName": "Yansong", 
            "type": "Person"
          }
        ], 
        "genre": "chapter", 
        "id": "sg:pub.10.1007/978-3-662-45924-9_30", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isFundedItemOf": [
          {
            "id": "sg:grant.7006109", 
            "type": "MonetaryGrant"
          }, 
          {
            "id": "sg:grant.7182349", 
            "type": "MonetaryGrant"
          }
        ], 
        "isPartOf": {
          "isbn": [
            "978-3-662-45923-2", 
            "978-3-662-45924-9"
          ], 
          "name": "Natural Language Processing and Chinese Computing", 
          "type": "Book"
        }, 
        "name": "Answering Natural Language Questions via Phrasal Semantic Parsing", 
        "pagination": "333-344", 
        "productId": [
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/978-3-662-45924-9_30"
            ]
          }, 
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "ca6a52f9ac5fc71818afc8905b138cb9e9d04d513a193e75fbe5c2ca975a92c4"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1042493657"
            ]
          }
        ], 
        "publisher": {
          "location": "Berlin, Heidelberg", 
          "name": "Springer Berlin Heidelberg", 
          "type": "Organisation"
        }, 
        "sameAs": [
          "https://doi.org/10.1007/978-3-662-45924-9_30", 
          "https://app.dimensions.ai/details/publication/pub.1042493657"
        ], 
        "sdDataset": "chapters", 
        "sdDatePublished": "2019-04-15T20:08", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000001_0000000264/records_8687_00000269.jsonl", 
        "type": "Chapter", 
        "url": "http://link.springer.com/10.1007/978-3-662-45924-9_30"
      }
    ]
     

    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.10.1007/978-3-662-45924-9_30'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-662-45924-9_30'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-662-45924-9_30'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-662-45924-9_30'


     

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

    137 TRIPLES      23 PREDICATES      37 URIs      20 LITERALS      8 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/978-3-662-45924-9_30 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N81a9d06d85ff4e138552d07949e3766a
    4 schema:citation sg:pub.10.1007/978-3-540-76298-0_52
    5 sg:pub.10.1007/978-3-642-22327-3_15
    6 sg:pub.10.1007/978-3-642-40802-1_30
    7 https://doi.org/10.1016/j.jal.2005.12.006
    8 https://doi.org/10.1145/2187836.2187923
    9 https://doi.org/10.3115/1118693.1118694
    10 https://doi.org/10.3115/1218955.1218970
    11 https://doi.org/10.3115/1599081.1599176
    12 https://doi.org/10.3115/v1/p14-1090
    13 https://doi.org/10.3115/v1/p14-1133
    14 schema:datePublished 2014
    15 schema:datePublishedReg 2014-01-01
    16 schema:description Understanding natural language questions and converting them into structured queries have been considered as a crucial way to help users access large scale structured knowledge bases. However, the task usually involves two main challenges: recognizing users’ query intention and mapping the involved semantic items against a given knowledge base (KB). In this paper, we propose an efficient pipeline framework to model a user’s query intention as a phrase level dependency DAG which is then instantiated regarding a specific KB to construct the final structured query. Our model benefits from the efficiency of linear structured prediction models and the separation of KB-independent and KB-related modelings. We evaluate our model on two datasets, and the experimental results showed that our method outperforms the state-of-the-art methods on the Free917 dataset, and, with limited training data from Free917, our model can smoothly adapt to new challenging dataset, WebQuestion, without extra training efforts while maintaining promising performances.
    17 schema:editor N795a25632ce94be8a30e039749527753
    18 schema:genre chapter
    19 schema:inLanguage en
    20 schema:isAccessibleForFree false
    21 schema:isPartOf Nf9975f90af74482a89c05547313a78d1
    22 schema:name Answering Natural Language Questions via Phrasal Semantic Parsing
    23 schema:pagination 333-344
    24 schema:productId N4c81e735c9ee41c08a3ea4413da104a2
    25 N80de13b657414c859be782a1efb2d279
    26 Ne488bc98fab7495cb7ac856221799633
    27 schema:publisher N339b08102d5648e5a1f3d020e16cc4c9
    28 schema:sameAs https://app.dimensions.ai/details/publication/pub.1042493657
    29 https://doi.org/10.1007/978-3-662-45924-9_30
    30 schema:sdDatePublished 2019-04-15T20:08
    31 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    32 schema:sdPublisher N09a5a759069f4ccfaa70e220b4eb4e4b
    33 schema:url http://link.springer.com/10.1007/978-3-662-45924-9_30
    34 sgo:license sg:explorer/license/
    35 sgo:sdDataset chapters
    36 rdf:type schema:Chapter
    37 N09a5a759069f4ccfaa70e220b4eb4e4b schema:name Springer Nature - SN SciGraph project
    38 rdf:type schema:Organization
    39 N1e7fd23a864545a6b3740778b64f8160 rdf:first sg:person.016004203227.20
    40 rdf:rest rdf:nil
    41 N24456d7186494141bfb35680b0f97d6a schema:familyName Zhao
    42 schema:givenName Dongyan
    43 rdf:type schema:Person
    44 N2d85404910c04e1c962675eba9dc00d5 rdf:first N8599e6e1dba64ac784aaf63a54f66c3b
    45 rdf:rest rdf:nil
    46 N339b08102d5648e5a1f3d020e16cc4c9 schema:location Berlin, Heidelberg
    47 schema:name Springer Berlin Heidelberg
    48 rdf:type schema:Organisation
    49 N45e4cec7b10f4d72931cd3b7e5127870 rdf:first Nc226ca0d7d6147a59037dec6b7bb8add
    50 rdf:rest N620b1d28aef54c069c7af41689a04428
    51 N4c81e735c9ee41c08a3ea4413da104a2 schema:name doi
    52 schema:value 10.1007/978-3-662-45924-9_30
    53 rdf:type schema:PropertyValue
    54 N620b1d28aef54c069c7af41689a04428 rdf:first sg:person.010630657066.08
    55 rdf:rest N1e7fd23a864545a6b3740778b64f8160
    56 N795a25632ce94be8a30e039749527753 rdf:first Nb895dbbc26754fcdbb1abbab12fb7cb1
    57 rdf:rest N80f289f4c36b42a89307d278d93c5e8c
    58 N80de13b657414c859be782a1efb2d279 schema:name dimensions_id
    59 schema:value pub.1042493657
    60 rdf:type schema:PropertyValue
    61 N80f289f4c36b42a89307d278d93c5e8c rdf:first Nd66ab7daa4894c5388281bf245ec6704
    62 rdf:rest N9cdb1014258444e0bbaab6b397a58920
    63 N81a9d06d85ff4e138552d07949e3766a rdf:first sg:person.010500262013.31
    64 rdf:rest N45e4cec7b10f4d72931cd3b7e5127870
    65 N8599e6e1dba64ac784aaf63a54f66c3b schema:familyName Feng
    66 schema:givenName Yansong
    67 rdf:type schema:Person
    68 N9cdb1014258444e0bbaab6b397a58920 rdf:first N24456d7186494141bfb35680b0f97d6a
    69 rdf:rest N2d85404910c04e1c962675eba9dc00d5
    70 Nb895dbbc26754fcdbb1abbab12fb7cb1 schema:familyName Zong
    71 schema:givenName Chengqing
    72 rdf:type schema:Person
    73 Nc226ca0d7d6147a59037dec6b7bb8add schema:affiliation https://www.grid.ac/institutes/grid.11135.37
    74 schema:familyName Zhang
    75 schema:givenName Sheng
    76 rdf:type schema:Person
    77 Nd66ab7daa4894c5388281bf245ec6704 schema:familyName Nie
    78 schema:givenName Jian-Yun
    79 rdf:type schema:Person
    80 Ne488bc98fab7495cb7ac856221799633 schema:name readcube_id
    81 schema:value ca6a52f9ac5fc71818afc8905b138cb9e9d04d513a193e75fbe5c2ca975a92c4
    82 rdf:type schema:PropertyValue
    83 Nf9975f90af74482a89c05547313a78d1 schema:isbn 978-3-662-45923-2
    84 978-3-662-45924-9
    85 schema:name Natural Language Processing and Chinese Computing
    86 rdf:type schema:Book
    87 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    88 schema:name Information and Computing Sciences
    89 rdf:type schema:DefinedTerm
    90 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    91 schema:name Artificial Intelligence and Image Processing
    92 rdf:type schema:DefinedTerm
    93 sg:grant.7006109 http://pending.schema.org/fundedItem sg:pub.10.1007/978-3-662-45924-9_30
    94 rdf:type schema:MonetaryGrant
    95 sg:grant.7182349 http://pending.schema.org/fundedItem sg:pub.10.1007/978-3-662-45924-9_30
    96 rdf:type schema:MonetaryGrant
    97 sg:person.010500262013.31 schema:affiliation https://www.grid.ac/institutes/grid.11135.37
    98 schema:familyName Xu
    99 schema:givenName Kun
    100 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010500262013.31
    101 rdf:type schema:Person
    102 sg:person.010630657066.08 schema:affiliation https://www.grid.ac/institutes/grid.11135.37
    103 schema:familyName Feng
    104 schema:givenName Yansong
    105 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010630657066.08
    106 rdf:type schema:Person
    107 sg:person.016004203227.20 schema:affiliation https://www.grid.ac/institutes/grid.11135.37
    108 schema:familyName Zhao
    109 schema:givenName Dongyan
    110 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016004203227.20
    111 rdf:type schema:Person
    112 sg:pub.10.1007/978-3-540-76298-0_52 schema:sameAs https://app.dimensions.ai/details/publication/pub.1028565626
    113 https://doi.org/10.1007/978-3-540-76298-0_52
    114 rdf:type schema:CreativeWork
    115 sg:pub.10.1007/978-3-642-22327-3_15 schema:sameAs https://app.dimensions.ai/details/publication/pub.1046687882
    116 https://doi.org/10.1007/978-3-642-22327-3_15
    117 rdf:type schema:CreativeWork
    118 sg:pub.10.1007/978-3-642-40802-1_30 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018433437
    119 https://doi.org/10.1007/978-3-642-40802-1_30
    120 rdf:type schema:CreativeWork
    121 https://doi.org/10.1016/j.jal.2005.12.006 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038280045
    122 rdf:type schema:CreativeWork
    123 https://doi.org/10.1145/2187836.2187923 schema:sameAs https://app.dimensions.ai/details/publication/pub.1019604077
    124 rdf:type schema:CreativeWork
    125 https://doi.org/10.3115/1118693.1118694 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099201575
    126 rdf:type schema:CreativeWork
    127 https://doi.org/10.3115/1218955.1218970 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099221196
    128 rdf:type schema:CreativeWork
    129 https://doi.org/10.3115/1599081.1599176 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099206013
    130 rdf:type schema:CreativeWork
    131 https://doi.org/10.3115/v1/p14-1090 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099110676
    132 rdf:type schema:CreativeWork
    133 https://doi.org/10.3115/v1/p14-1133 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099110721
    134 rdf:type schema:CreativeWork
    135 https://www.grid.ac/institutes/grid.11135.37 schema:alternateName Peking University
    136 schema:name Peking University, Beijing, China
    137 rdf:type schema:Organization
     




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


    ...