Query-dependent learning to rank for cross-lingual information retrieval View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2019-06

AUTHORS

Elham Ghanbari, Azadeh Shakery

ABSTRACT

Learning to rank (LTR), as a machine learning technique for ranking tasks, has become one of the most popular research topics in the area of information retrieval (IR). Cross-lingual information retrieval (CLIR), in which the language of the query is different from the language of the documents, is one of the important IR tasks that can potentially benefit from LTR. Our focus in this paper is the use of LTR for CLIR. To rank the documents in the target language in response to the query in the source language, we propose a local query-dependent approach based on LTR for CLIR, which is called LQ-DLTR for CLIR. The core idea of LQ-DLTR for CLIR is the use of the local characteristics of similar queries to construct the LTR model, instead of using a single global ranking model for all queries. Since the query and the documents are in different languages, the traditional features that are used in LTR cannot be used directly for CLIR. Thus, defining appropriate features is a major step in the use of LTR for CLIR. In this paper, three categories of cross-lingual features are defined: query–document features, document features, and query features. To define the cross-lingual features, translation resources are used to fill the gap between the documents and the queries. Then, in LQ-DLTR for CLIR, a neighborhood of similar queries based on cross-lingual query features is used to create a local ranking function by the LTR algorithm for a given query. The LTR algorithm uses two cross-lingual feature sets, namely document features and query–document features, to learn the model. The query features that are used to identify the neighbors are not involved in the learning phase. Experimental results indicate that the CLIR performance improves with the use of cross-lingual features that use several translations and their probabilities to compute the features, compared to the use of monolingual features in traditional LTR, which translate a query according to the best translation and ignore the probabilities. Moreover, experimental results show that LQ-DLTR for CLIR outperforms the baseline information retrieval methods and other LTR ranking models in terms of the MAP and NDCG measures. More... »

PAGES

711-743

References to SciGraph publications

  • 2009. Joint Ranking for Multilingual Web Search in ADVANCES IN INFORMATION RETRIEVAL
  • 2015-06. Multilingual information retrieval in the language modeling framework in INFORMATION RETRIEVAL JOURNAL
  • 2011. Multiview Semi-supervised Learning for Ranking Multilingual Documents in MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES
  • 2004. Inferring Query Performance Using Pre-retrieval Predictors in STRING PROCESSING AND INFORMATION RETRIEVAL
  • 2011. Combining Query Translation Techniques to Improve Cross-Language Information Retrieval in ADVANCES IN INFORMATION RETRIEVAL
  • 2008. Effective Pre-retrieval Query Performance Prediction Using Similarity and Variability Evidence in ADVANCES IN INFORMATION RETRIEVAL
  • 2011. Learning to Rank for Information Retrieval in NONE
  • 2013. Exploiting Multiple Translation Resources for English-Persian Cross Language Information Retrieval in INFORMATION ACCESS EVALUATION. MULTILINGUALITY, MULTIMODALITY, AND VISUALIZATION
  • 2016. The CLEF Monolingual Grid of Points in EXPERIMENTAL IR MEETS MULTILINGUALITY, MULTIMODALITY, AND INTERACTION
  • 2013. A Language Modeling Approach for Extracting Translation Knowledge from Comparable Corpora in ADVANCES IN INFORMATION RETRIEVAL
  • 2016. Cross Lingual Information Retrieval (CLIR): Review of Tools, Challenges and Translation Approaches in INFORMATION SYSTEMS DESIGN AND INTELLIGENT APPLICATIONS
  • 2004-01. Dictionary-Based Cross-Language Information Retrieval: Learning Experiences from CLEF 2000–2002 in INFORMATION RETRIEVAL JOURNAL
  • 2010. Learning to Select a Ranking Function in ADVANCES IN INFORMATION RETRIEVAL
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/s10115-018-1232-8

    DOI

    http://dx.doi.org/10.1007/s10115-018-1232-8

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1105301567


    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": "University of Tehran", 
              "id": "https://www.grid.ac/institutes/grid.46072.37", 
              "name": [
                "School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Ghanbari", 
            "givenName": "Elham", 
            "id": "sg:person.014105262503.09", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014105262503.09"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Institute for Research in Fundamental Sciences", 
              "id": "https://www.grid.ac/institutes/grid.418744.a", 
              "name": [
                "School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran", 
                "School of Computer Science, Institute for Research in Fundamental Sciences (IPM), Tehran, Iran"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Shakery", 
            "givenName": "Azadeh", 
            "id": "sg:person.010637536071.10", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010637536071.10"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "https://doi.org/10.1145/1277741.1277809", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1001815339"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-23808-6_29", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1003283523", 
              "https://doi.org/10.1007/978-3-642-23808-6_29"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-23808-6_29", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1003283523", 
              "https://doi.org/10.1007/978-3-642-23808-6_29"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.knosys.2009.05.002", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1007932186"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/984321.984322", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1008412667"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1023/b:inrt.0000009442.34054.55", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1008954989", 
              "https://doi.org/10.1023/b:inrt.0000009442.34054.55"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.7202/029804ar", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1014762859"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/1273496.1273513", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1015815450"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/2766462.2767805", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1015944584"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.ipm.2015.08.001", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1017513478"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/1390334.1390370", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1018063997"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/1390334.1390356", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1020175594"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/564376.564383", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1021177964"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-319-44564-9_2", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1021745673", 
              "https://doi.org/10.1007/978-3-319-44564-9_2"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s10791-015-9255-1", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1023405217", 
              "https://doi.org/10.1007/s10791-015-9255-1"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1002/asi.23153", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1023644236"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-78646-7_8", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1024072617", 
              "https://doi.org/10.1007/978-3-540-78646-7_8"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-78646-7_8", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1024072617", 
              "https://doi.org/10.1007/978-3-540-78646-7_8"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-30213-1_5", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1024509036", 
              "https://doi.org/10.1007/978-3-540-30213-1_5"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-30213-1_5", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1024509036", 
              "https://doi.org/10.1007/978-3-540-30213-1_5"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-81-322-2755-7_72", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1025398332", 
              "https://doi.org/10.1007/978-81-322-2755-7_72"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/564376.564429", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1025673235"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/860435.860497", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1028636753"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/2644807", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1031732207"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-14267-3", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1033108348", 
              "https://doi.org/10.1007/978-3-642-14267-3"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-14267-3", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1033108348", 
              "https://doi.org/10.1007/978-3-642-14267-3"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-40802-1_11", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1035169754", 
              "https://doi.org/10.1007/978-3-642-40802-1_11"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/s0169-7552(98)00110-x", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1035913093"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.ipm.2009.12.002", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1039458635"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1002/asi.20011", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1040741941"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-12275-0_13", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1041126694", 
              "https://doi.org/10.1007/978-3-642-12275-0_13"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-12275-0_13", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1041126694", 
              "https://doi.org/10.1007/978-3-642-12275-0_13"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-00958-7_13", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1042362326", 
              "https://doi.org/10.1007/978-3-642-00958-7_13"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-00958-7_13", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1042362326", 
              "https://doi.org/10.1007/978-3-642-00958-7_13"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1162/089120103321337421", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1042637788"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.ipm.2016.08.001", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1044037092"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-36973-5_51", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1045017776", 
              "https://doi.org/10.1007/978-3-642-36973-5_51"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-20161-5_77", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1047094708", 
              "https://doi.org/10.1007/978-3-642-20161-5_77"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-20161-5_77", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1047094708", 
              "https://doi.org/10.1007/978-3-642-20161-5_77"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/2766462.2767752", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1047657697"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/582415.582418", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1050459672"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.11591/ij-ict.v2i1.1505", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1063285099"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1561/1500000008", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1068001274"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.2200/s00266ed1v01y201005hlt008", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1069288148"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.2200/s00607ed2v01y201410hlt026", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1069288491"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.21236/ada459304", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1091745410"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icacsis.2014.7065896", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094581422"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/aisp.2012.6313739", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095359918"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/waim.2008.35", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095610764"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1017/cbo9780511809071", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1098672059"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.3115/1690219.1690296", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099238618"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2019-06", 
        "datePublishedReg": "2019-06-01", 
        "description": "Learning to rank (LTR), as a machine learning technique for ranking tasks, has become one of the most popular research topics in the area of information retrieval (IR). Cross-lingual information retrieval (CLIR), in which the language of the query is different from the language of the documents, is one of the important IR tasks that can potentially benefit from LTR. Our focus in this paper is the use of LTR for CLIR. To rank the documents in the target language in response to the query in the source language, we propose a local query-dependent approach based on LTR for CLIR, which is called LQ-DLTR for CLIR. The core idea of LQ-DLTR for CLIR is the use of the local characteristics of similar queries to construct the LTR model, instead of using a single global ranking model for all queries. Since the query and the documents are in different languages, the traditional features that are used in LTR cannot be used directly for CLIR. Thus, defining appropriate features is a major step in the use of LTR for CLIR. In this paper, three categories of cross-lingual features are defined: query\u2013document features, document features, and query features. To define the cross-lingual features, translation resources are used to fill the gap between the documents and the queries. Then, in LQ-DLTR for CLIR, a neighborhood of similar queries based on cross-lingual query features is used to create a local ranking function by the LTR algorithm for a given query. The LTR algorithm uses two cross-lingual feature sets, namely document features and query\u2013document features, to learn the model. The query features that are used to identify the neighbors are not involved in the learning phase. Experimental results indicate that the CLIR performance improves with the use of cross-lingual features that use several translations and their probabilities to compute the features, compared to the use of monolingual features in traditional LTR, which translate a query according to the best translation and ignore the probabilities. Moreover, experimental results show that LQ-DLTR for CLIR outperforms the baseline information retrieval methods and other LTR ranking models in terms of the MAP and NDCG measures.", 
        "genre": "research_article", 
        "id": "sg:pub.10.1007/s10115-018-1232-8", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isPartOf": [
          {
            "id": "sg:journal.1041769", 
            "issn": [
              "0219-1377", 
              "0219-3116"
            ], 
            "name": "Knowledge and Information Systems", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "3", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "59"
          }
        ], 
        "name": "Query-dependent learning to rank for cross-lingual information retrieval", 
        "pagination": "711-743", 
        "productId": [
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "e8935bcc00326e6c1568be15458b2d83af890b4e1762001bad55347f0eb1bc73"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/s10115-018-1232-8"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1105301567"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1007/s10115-018-1232-8", 
          "https://app.dimensions.ai/details/publication/pub.1105301567"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2019-04-11T12:52", 
        "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/v90/0000000364_0000000364/records_72834_00000001.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://link.springer.com/10.1007%2Fs10115-018-1232-8"
      }
    ]
     

    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/s10115-018-1232-8'

    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/s10115-018-1232-8'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s10115-018-1232-8'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s10115-018-1232-8'


     

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

    217 TRIPLES      21 PREDICATES      71 URIs      19 LITERALS      7 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/s10115-018-1232-8 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author Na7ecc76607be4605938cbb0ada20ad67
    4 schema:citation sg:pub.10.1007/978-3-319-44564-9_2
    5 sg:pub.10.1007/978-3-540-30213-1_5
    6 sg:pub.10.1007/978-3-540-78646-7_8
    7 sg:pub.10.1007/978-3-642-00958-7_13
    8 sg:pub.10.1007/978-3-642-12275-0_13
    9 sg:pub.10.1007/978-3-642-14267-3
    10 sg:pub.10.1007/978-3-642-20161-5_77
    11 sg:pub.10.1007/978-3-642-23808-6_29
    12 sg:pub.10.1007/978-3-642-36973-5_51
    13 sg:pub.10.1007/978-3-642-40802-1_11
    14 sg:pub.10.1007/978-81-322-2755-7_72
    15 sg:pub.10.1007/s10791-015-9255-1
    16 sg:pub.10.1023/b:inrt.0000009442.34054.55
    17 https://doi.org/10.1002/asi.20011
    18 https://doi.org/10.1002/asi.23153
    19 https://doi.org/10.1016/j.ipm.2009.12.002
    20 https://doi.org/10.1016/j.ipm.2015.08.001
    21 https://doi.org/10.1016/j.ipm.2016.08.001
    22 https://doi.org/10.1016/j.knosys.2009.05.002
    23 https://doi.org/10.1016/s0169-7552(98)00110-x
    24 https://doi.org/10.1017/cbo9780511809071
    25 https://doi.org/10.1109/aisp.2012.6313739
    26 https://doi.org/10.1109/icacsis.2014.7065896
    27 https://doi.org/10.1109/waim.2008.35
    28 https://doi.org/10.1145/1273496.1273513
    29 https://doi.org/10.1145/1277741.1277809
    30 https://doi.org/10.1145/1390334.1390356
    31 https://doi.org/10.1145/1390334.1390370
    32 https://doi.org/10.1145/2644807
    33 https://doi.org/10.1145/2766462.2767752
    34 https://doi.org/10.1145/2766462.2767805
    35 https://doi.org/10.1145/564376.564383
    36 https://doi.org/10.1145/564376.564429
    37 https://doi.org/10.1145/582415.582418
    38 https://doi.org/10.1145/860435.860497
    39 https://doi.org/10.1145/984321.984322
    40 https://doi.org/10.11591/ij-ict.v2i1.1505
    41 https://doi.org/10.1162/089120103321337421
    42 https://doi.org/10.1561/1500000008
    43 https://doi.org/10.21236/ada459304
    44 https://doi.org/10.2200/s00266ed1v01y201005hlt008
    45 https://doi.org/10.2200/s00607ed2v01y201410hlt026
    46 https://doi.org/10.3115/1690219.1690296
    47 https://doi.org/10.7202/029804ar
    48 schema:datePublished 2019-06
    49 schema:datePublishedReg 2019-06-01
    50 schema:description Learning to rank (LTR), as a machine learning technique for ranking tasks, has become one of the most popular research topics in the area of information retrieval (IR). Cross-lingual information retrieval (CLIR), in which the language of the query is different from the language of the documents, is one of the important IR tasks that can potentially benefit from LTR. Our focus in this paper is the use of LTR for CLIR. To rank the documents in the target language in response to the query in the source language, we propose a local query-dependent approach based on LTR for CLIR, which is called LQ-DLTR for CLIR. The core idea of LQ-DLTR for CLIR is the use of the local characteristics of similar queries to construct the LTR model, instead of using a single global ranking model for all queries. Since the query and the documents are in different languages, the traditional features that are used in LTR cannot be used directly for CLIR. Thus, defining appropriate features is a major step in the use of LTR for CLIR. In this paper, three categories of cross-lingual features are defined: query–document features, document features, and query features. To define the cross-lingual features, translation resources are used to fill the gap between the documents and the queries. Then, in LQ-DLTR for CLIR, a neighborhood of similar queries based on cross-lingual query features is used to create a local ranking function by the LTR algorithm for a given query. The LTR algorithm uses two cross-lingual feature sets, namely document features and query–document features, to learn the model. The query features that are used to identify the neighbors are not involved in the learning phase. Experimental results indicate that the CLIR performance improves with the use of cross-lingual features that use several translations and their probabilities to compute the features, compared to the use of monolingual features in traditional LTR, which translate a query according to the best translation and ignore the probabilities. Moreover, experimental results show that LQ-DLTR for CLIR outperforms the baseline information retrieval methods and other LTR ranking models in terms of the MAP and NDCG measures.
    51 schema:genre research_article
    52 schema:inLanguage en
    53 schema:isAccessibleForFree false
    54 schema:isPartOf N1f4be13776f445929c74e803408b3ebd
    55 Na38e43f97b9f4244970f9c5343d15eda
    56 sg:journal.1041769
    57 schema:name Query-dependent learning to rank for cross-lingual information retrieval
    58 schema:pagination 711-743
    59 schema:productId N70e2a65b6d894050b75473d0f8037516
    60 N76d0f51c8704465d84f79ea862c07fd2
    61 Nf9e4c55a93834ff987ef1051ff228209
    62 schema:sameAs https://app.dimensions.ai/details/publication/pub.1105301567
    63 https://doi.org/10.1007/s10115-018-1232-8
    64 schema:sdDatePublished 2019-04-11T12:52
    65 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    66 schema:sdPublisher N204b9ee7003a46c88624804a66285c14
    67 schema:url https://link.springer.com/10.1007%2Fs10115-018-1232-8
    68 sgo:license sg:explorer/license/
    69 sgo:sdDataset articles
    70 rdf:type schema:ScholarlyArticle
    71 N1f4be13776f445929c74e803408b3ebd schema:issueNumber 3
    72 rdf:type schema:PublicationIssue
    73 N204b9ee7003a46c88624804a66285c14 schema:name Springer Nature - SN SciGraph project
    74 rdf:type schema:Organization
    75 N5504f2b65e3f4d428b8007c092934ebe rdf:first sg:person.010637536071.10
    76 rdf:rest rdf:nil
    77 N70e2a65b6d894050b75473d0f8037516 schema:name doi
    78 schema:value 10.1007/s10115-018-1232-8
    79 rdf:type schema:PropertyValue
    80 N76d0f51c8704465d84f79ea862c07fd2 schema:name readcube_id
    81 schema:value e8935bcc00326e6c1568be15458b2d83af890b4e1762001bad55347f0eb1bc73
    82 rdf:type schema:PropertyValue
    83 Na38e43f97b9f4244970f9c5343d15eda schema:volumeNumber 59
    84 rdf:type schema:PublicationVolume
    85 Na7ecc76607be4605938cbb0ada20ad67 rdf:first sg:person.014105262503.09
    86 rdf:rest N5504f2b65e3f4d428b8007c092934ebe
    87 Nf9e4c55a93834ff987ef1051ff228209 schema:name dimensions_id
    88 schema:value pub.1105301567
    89 rdf:type schema:PropertyValue
    90 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    91 schema:name Information and Computing Sciences
    92 rdf:type schema:DefinedTerm
    93 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    94 schema:name Artificial Intelligence and Image Processing
    95 rdf:type schema:DefinedTerm
    96 sg:journal.1041769 schema:issn 0219-1377
    97 0219-3116
    98 schema:name Knowledge and Information Systems
    99 rdf:type schema:Periodical
    100 sg:person.010637536071.10 schema:affiliation https://www.grid.ac/institutes/grid.418744.a
    101 schema:familyName Shakery
    102 schema:givenName Azadeh
    103 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010637536071.10
    104 rdf:type schema:Person
    105 sg:person.014105262503.09 schema:affiliation https://www.grid.ac/institutes/grid.46072.37
    106 schema:familyName Ghanbari
    107 schema:givenName Elham
    108 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014105262503.09
    109 rdf:type schema:Person
    110 sg:pub.10.1007/978-3-319-44564-9_2 schema:sameAs https://app.dimensions.ai/details/publication/pub.1021745673
    111 https://doi.org/10.1007/978-3-319-44564-9_2
    112 rdf:type schema:CreativeWork
    113 sg:pub.10.1007/978-3-540-30213-1_5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024509036
    114 https://doi.org/10.1007/978-3-540-30213-1_5
    115 rdf:type schema:CreativeWork
    116 sg:pub.10.1007/978-3-540-78646-7_8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024072617
    117 https://doi.org/10.1007/978-3-540-78646-7_8
    118 rdf:type schema:CreativeWork
    119 sg:pub.10.1007/978-3-642-00958-7_13 schema:sameAs https://app.dimensions.ai/details/publication/pub.1042362326
    120 https://doi.org/10.1007/978-3-642-00958-7_13
    121 rdf:type schema:CreativeWork
    122 sg:pub.10.1007/978-3-642-12275-0_13 schema:sameAs https://app.dimensions.ai/details/publication/pub.1041126694
    123 https://doi.org/10.1007/978-3-642-12275-0_13
    124 rdf:type schema:CreativeWork
    125 sg:pub.10.1007/978-3-642-14267-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1033108348
    126 https://doi.org/10.1007/978-3-642-14267-3
    127 rdf:type schema:CreativeWork
    128 sg:pub.10.1007/978-3-642-20161-5_77 schema:sameAs https://app.dimensions.ai/details/publication/pub.1047094708
    129 https://doi.org/10.1007/978-3-642-20161-5_77
    130 rdf:type schema:CreativeWork
    131 sg:pub.10.1007/978-3-642-23808-6_29 schema:sameAs https://app.dimensions.ai/details/publication/pub.1003283523
    132 https://doi.org/10.1007/978-3-642-23808-6_29
    133 rdf:type schema:CreativeWork
    134 sg:pub.10.1007/978-3-642-36973-5_51 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045017776
    135 https://doi.org/10.1007/978-3-642-36973-5_51
    136 rdf:type schema:CreativeWork
    137 sg:pub.10.1007/978-3-642-40802-1_11 schema:sameAs https://app.dimensions.ai/details/publication/pub.1035169754
    138 https://doi.org/10.1007/978-3-642-40802-1_11
    139 rdf:type schema:CreativeWork
    140 sg:pub.10.1007/978-81-322-2755-7_72 schema:sameAs https://app.dimensions.ai/details/publication/pub.1025398332
    141 https://doi.org/10.1007/978-81-322-2755-7_72
    142 rdf:type schema:CreativeWork
    143 sg:pub.10.1007/s10791-015-9255-1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1023405217
    144 https://doi.org/10.1007/s10791-015-9255-1
    145 rdf:type schema:CreativeWork
    146 sg:pub.10.1023/b:inrt.0000009442.34054.55 schema:sameAs https://app.dimensions.ai/details/publication/pub.1008954989
    147 https://doi.org/10.1023/b:inrt.0000009442.34054.55
    148 rdf:type schema:CreativeWork
    149 https://doi.org/10.1002/asi.20011 schema:sameAs https://app.dimensions.ai/details/publication/pub.1040741941
    150 rdf:type schema:CreativeWork
    151 https://doi.org/10.1002/asi.23153 schema:sameAs https://app.dimensions.ai/details/publication/pub.1023644236
    152 rdf:type schema:CreativeWork
    153 https://doi.org/10.1016/j.ipm.2009.12.002 schema:sameAs https://app.dimensions.ai/details/publication/pub.1039458635
    154 rdf:type schema:CreativeWork
    155 https://doi.org/10.1016/j.ipm.2015.08.001 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017513478
    156 rdf:type schema:CreativeWork
    157 https://doi.org/10.1016/j.ipm.2016.08.001 schema:sameAs https://app.dimensions.ai/details/publication/pub.1044037092
    158 rdf:type schema:CreativeWork
    159 https://doi.org/10.1016/j.knosys.2009.05.002 schema:sameAs https://app.dimensions.ai/details/publication/pub.1007932186
    160 rdf:type schema:CreativeWork
    161 https://doi.org/10.1016/s0169-7552(98)00110-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1035913093
    162 rdf:type schema:CreativeWork
    163 https://doi.org/10.1017/cbo9780511809071 schema:sameAs https://app.dimensions.ai/details/publication/pub.1098672059
    164 rdf:type schema:CreativeWork
    165 https://doi.org/10.1109/aisp.2012.6313739 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095359918
    166 rdf:type schema:CreativeWork
    167 https://doi.org/10.1109/icacsis.2014.7065896 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094581422
    168 rdf:type schema:CreativeWork
    169 https://doi.org/10.1109/waim.2008.35 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095610764
    170 rdf:type schema:CreativeWork
    171 https://doi.org/10.1145/1273496.1273513 schema:sameAs https://app.dimensions.ai/details/publication/pub.1015815450
    172 rdf:type schema:CreativeWork
    173 https://doi.org/10.1145/1277741.1277809 schema:sameAs https://app.dimensions.ai/details/publication/pub.1001815339
    174 rdf:type schema:CreativeWork
    175 https://doi.org/10.1145/1390334.1390356 schema:sameAs https://app.dimensions.ai/details/publication/pub.1020175594
    176 rdf:type schema:CreativeWork
    177 https://doi.org/10.1145/1390334.1390370 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018063997
    178 rdf:type schema:CreativeWork
    179 https://doi.org/10.1145/2644807 schema:sameAs https://app.dimensions.ai/details/publication/pub.1031732207
    180 rdf:type schema:CreativeWork
    181 https://doi.org/10.1145/2766462.2767752 schema:sameAs https://app.dimensions.ai/details/publication/pub.1047657697
    182 rdf:type schema:CreativeWork
    183 https://doi.org/10.1145/2766462.2767805 schema:sameAs https://app.dimensions.ai/details/publication/pub.1015944584
    184 rdf:type schema:CreativeWork
    185 https://doi.org/10.1145/564376.564383 schema:sameAs https://app.dimensions.ai/details/publication/pub.1021177964
    186 rdf:type schema:CreativeWork
    187 https://doi.org/10.1145/564376.564429 schema:sameAs https://app.dimensions.ai/details/publication/pub.1025673235
    188 rdf:type schema:CreativeWork
    189 https://doi.org/10.1145/582415.582418 schema:sameAs https://app.dimensions.ai/details/publication/pub.1050459672
    190 rdf:type schema:CreativeWork
    191 https://doi.org/10.1145/860435.860497 schema:sameAs https://app.dimensions.ai/details/publication/pub.1028636753
    192 rdf:type schema:CreativeWork
    193 https://doi.org/10.1145/984321.984322 schema:sameAs https://app.dimensions.ai/details/publication/pub.1008412667
    194 rdf:type schema:CreativeWork
    195 https://doi.org/10.11591/ij-ict.v2i1.1505 schema:sameAs https://app.dimensions.ai/details/publication/pub.1063285099
    196 rdf:type schema:CreativeWork
    197 https://doi.org/10.1162/089120103321337421 schema:sameAs https://app.dimensions.ai/details/publication/pub.1042637788
    198 rdf:type schema:CreativeWork
    199 https://doi.org/10.1561/1500000008 schema:sameAs https://app.dimensions.ai/details/publication/pub.1068001274
    200 rdf:type schema:CreativeWork
    201 https://doi.org/10.21236/ada459304 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091745410
    202 rdf:type schema:CreativeWork
    203 https://doi.org/10.2200/s00266ed1v01y201005hlt008 schema:sameAs https://app.dimensions.ai/details/publication/pub.1069288148
    204 rdf:type schema:CreativeWork
    205 https://doi.org/10.2200/s00607ed2v01y201410hlt026 schema:sameAs https://app.dimensions.ai/details/publication/pub.1069288491
    206 rdf:type schema:CreativeWork
    207 https://doi.org/10.3115/1690219.1690296 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099238618
    208 rdf:type schema:CreativeWork
    209 https://doi.org/10.7202/029804ar schema:sameAs https://app.dimensions.ai/details/publication/pub.1014762859
    210 rdf:type schema:CreativeWork
    211 https://www.grid.ac/institutes/grid.418744.a schema:alternateName Institute for Research in Fundamental Sciences
    212 schema:name School of Computer Science, Institute for Research in Fundamental Sciences (IPM), Tehran, Iran
    213 School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran
    214 rdf:type schema:Organization
    215 https://www.grid.ac/institutes/grid.46072.37 schema:alternateName University of Tehran
    216 schema:name School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran
    217 rdf:type schema:Organization
     




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


    ...