Conference paper Open Access

A Domain Independent Semantic Measure for Keyword Sense Disambiguation

María G. Buey; Carlos Bobed; Jorge Gracia; Eduardo Mena


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/29266608-26e2-42cd-ab65-6cd02ebcccbc/SAC_SWA2021_Semantic_Relatedness_for_Keyword_Disambiguation.pdf"
      }, 
      "checksum": "md5:c9b9a5649d0595bce2f1225115a6d014", 
      "bucket": "29266608-26e2-42cd-ab65-6cd02ebcccbc", 
      "key": "SAC_SWA2021_Semantic_Relatedness_for_Keyword_Disambiguation.pdf", 
      "type": "pdf", 
      "size": 484729
    }
  ], 
  "owners": [
    78313
  ], 
  "doi": "10.5281/zenodo.4631685", 
  "stats": {
    "version_unique_downloads": 33.0, 
    "unique_views": 76.0, 
    "views": 88.0, 
    "version_views": 88.0, 
    "unique_downloads": 33.0, 
    "version_unique_views": 76.0, 
    "volume": 15996057.0, 
    "version_downloads": 33.0, 
    "downloads": 33.0, 
    "version_volume": 15996057.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.4631685", 
    "conceptdoi": "https://doi.org/10.5281/zenodo.4631684", 
    "bucket": "https://zenodo.org/api/files/29266608-26e2-42cd-ab65-6cd02ebcccbc", 
    "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.4631684.svg", 
    "html": "https://zenodo.org/record/4631685", 
    "latest_html": "https://zenodo.org/record/4631685", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.4631685.svg", 
    "latest": "https://zenodo.org/api/records/4631685"
  }, 
  "conceptdoi": "10.5281/zenodo.4631684", 
  "created": "2021-03-23T18:15:51.163034+00:00", 
  "updated": "2021-03-31T15:50:56.754578+00:00", 
  "conceptrecid": "4631684", 
  "revision": 4, 
  "id": 4631685, 
  "metadata": {
    "access_right_category": "success", 
    "part_of": {
      "title": "Proceedings of 36th ACM/SIGAPP Symposium On Applied Computing"
    }, 
    "doi": "10.5281/zenodo.4631685", 
    "version": "pre-published version", 
    "license": {
      "id": "CC-BY-4.0"
    }, 
    "title": "A Domain Independent Semantic Measure for Keyword Sense Disambiguation", 
    "related_identifiers": [
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.4631684", 
        "relation": "isVersionOf"
      }
    ], 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "4631684"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "4631685"
          }
        }
      ]
    }, 
    "imprint": {
      "publisher": "ACM"
    }, 
    "grants": [
      {
        "code": "825182", 
        "links": {
          "self": "https://zenodo.org/api/grants/10.13039/501100000780::825182"
        }, 
        "title": "Ready-to-use Multilingual Linked Language Data for Knowledge Services across Sectors", 
        "acronym": "Pret-a-LLOD", 
        "program": "H2020", 
        "funder": {
          "doi": "10.13039/501100000780", 
          "acronyms": [], 
          "name": "European Commission", 
          "links": {
            "self": "https://zenodo.org/api/funders/10.13039/501100000780"
          }
        }
      }, 
      {
        "code": "780602", 
        "links": {
          "self": "https://zenodo.org/api/grants/10.13039/501100000780::780602"
        }, 
        "title": "Building the Legal Knowledge Graph for Smart Compliance Services in Multilingual Europe", 
        "acronym": "Lynx", 
        "program": "H2020", 
        "funder": {
          "doi": "10.13039/501100000780", 
          "acronyms": [], 
          "name": "European Commission", 
          "links": {
            "self": "https://zenodo.org/api/funders/10.13039/501100000780"
          }
        }
      }
    ], 
    "communities": [
      {
        "id": "lynx"
      }, 
      {
        "id": "pret-a-llod"
      }
    ], 
    "publication_date": "2021-03-23", 
    "creators": [
      {
        "affiliation": "Everis/NTT Data", 
        "name": "Mar\u00eda G. Buey"
      }, 
      {
        "affiliation": "University of Zaragoza", 
        "name": "Carlos Bobed"
      }, 
      {
        "orcid": "0000-0001-6452-7627", 
        "affiliation": "University of Zaragoza", 
        "name": "Jorge Gracia"
      }, 
      {
        "affiliation": "University of Zaragoza", 
        "name": "Eduardo Mena"
      }
    ], 
    "meeting": {
      "acronym": "SAC 2021", 
      "url": "https://www.sigapp.org/sac/sac2021/index.html", 
      "dates": "22-26", 
      "place": "online", 
      "title": "36th ACM/SIGAPP Symposium On Applied Computing"
    }, 
    "access_right": "open", 
    "resource_type": {
      "subtype": "conferencepaper", 
      "type": "publication", 
      "title": "Conference paper"
    }, 
    "description": "<p>Understanding the user&#39;s intention is crucial for many tasks that involve human-machine interaction. To that end, word sense disambiguation (WSD) techniques play an important role. WSD techniques typically require well-formed sentences as context to operate, as well as pre-defined catalogues of word senses. However, there are some scenarios on the Web where such conditions do not apply well, such as when there is a need to disambiguate keywords from a query, or sets of tags describing any Web resource, where the context does not come as well-formed sentences. In this paper, we propose an approach to disambiguate sets of keywords by linking them to concepts of a given ontology that is not known at training time. Our approach grounds on a semantic relatedness measure between words and concepts, and explores different disambiguation algorithms to study the contribution of both word and sentence-level representations. We focus on situations where the available linguistic information is very scarce (e.g., keyword-based / Web search queries), hampering natural language based approaches. Experimental results show the feasibility of our approach in general and in specific knowledge domains without previous training for the target domain.</p>"
  }
}
88
33
views
downloads
All versions This version
Views 8888
Downloads 3333
Data volume 16.0 MB16.0 MB
Unique views 7676
Unique downloads 3333

Share

Cite as