Project deliverable Open Access

BigDataGrapes D3.4 - Linguistic Pipelines for Semantic Enrichment

Yankova; Milena; Alexiev, Vladimir; Primov, Todor; Rusinov, Nikola


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/3ef47411-3676-43f4-b0c2-d44e53aef5ae/D3.4%20Linguistic%20Pipelines%20for%20Semantic%20Enrichment%20%28submitted%20to%20EC%29.pdf"
      }, 
      "checksum": "md5:b4304643b2b4857162c64cf60fa49f3d", 
      "bucket": "3ef47411-3676-43f4-b0c2-d44e53aef5ae", 
      "key": "D3.4 Linguistic Pipelines for Semantic Enrichment (submitted to EC).pdf", 
      "type": "pdf", 
      "size": 1469395
    }
  ], 
  "owners": [
    48887
  ], 
  "doi": "10.5281/zenodo.2449669", 
  "stats": {
    "version_unique_downloads": 19.0, 
    "unique_views": 18.0, 
    "views": 20.0, 
    "downloads": 21.0, 
    "unique_downloads": 19.0, 
    "version_unique_views": 18.0, 
    "volume": 30857295.0, 
    "version_downloads": 21.0, 
    "version_views": 20.0, 
    "version_volume": 30857295.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.2449669", 
    "conceptdoi": "https://doi.org/10.5281/zenodo.2449668", 
    "bucket": "https://zenodo.org/api/files/3ef47411-3676-43f4-b0c2-d44e53aef5ae", 
    "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.2449668.svg", 
    "html": "https://zenodo.org/record/2449669", 
    "latest_html": "https://zenodo.org/record/2449669", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.2449669.svg", 
    "latest": "https://zenodo.org/api/records/2449669"
  }, 
  "conceptdoi": "10.5281/zenodo.2449668", 
  "created": "2018-12-20T12:13:25.108890+00:00", 
  "updated": "2019-04-10T03:00:11.666528+00:00", 
  "conceptrecid": "2449668", 
  "revision": 5, 
  "id": 2449669, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.2449669", 
    "version": "1.0 | Final", 
    "license": {
      "id": "CC-BY-4.0"
    }, 
    "title": "BigDataGrapes D3.4 - Linguistic Pipelines for Semantic Enrichment", 
    "language": "eng", 
    "related_identifiers": [
      {
        "scheme": "doi", 
        "relation": "isVersionOf", 
        "identifier": "10.5281/zenodo.2449668"
      }
    ], 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "2449668"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "2449669"
          }
        }
      ]
    }, 
    "communities": [
      {
        "id": "bigdatagrapes"
      }
    ], 
    "grants": [
      {
        "code": "780751", 
        "links": {
          "self": "https://zenodo.org/api/grants/10.13039/501100000780::780751"
        }, 
        "title": "Big Data to Enable Global Disruption of the Grapevine-powered Industries", 
        "acronym": "BigDataGrapes", 
        "program": "H2020", 
        "funder": {
          "doi": "10.13039/501100000780", 
          "acronyms": [
            "EC"
          ], 
          "name": "European Commission", 
          "links": {
            "self": "https://zenodo.org/api/funders/10.13039/501100000780"
          }
        }
      }
    ], 
    "keywords": [
      "Semantic; linguistic pipelines; text analytics"
    ], 
    "publication_date": "2018-12-20", 
    "creators": [
      {
        "affiliation": "ONTOTEXT", 
        "name": "Yankova; Milena"
      }, 
      {
        "orcid": "0000-0001-7508-7428", 
        "affiliation": "ONTOTEXT", 
        "name": "Alexiev, Vladimir"
      }, 
      {
        "affiliation": "ONTOTEXT", 
        "name": "Primov, Todor"
      }, 
      {
        "affiliation": "ONTOTEXT", 
        "name": "Rusinov, Nikola"
      }
    ], 
    "access_right": "open", 
    "resource_type": {
      "subtype": "deliverable", 
      "type": "publication", 
      "title": "Project deliverable"
    }, 
    "description": "<p>This deliverable is the first report on the progress of T3.4 Semantic Enrichment. It will describe the progress on the design of advanced text analytics pipelines aiming to extract and semantically annotate information from unstructured textual data sources from the Big Data Grapes (BDG) data pool. It will describe in detail a proposed approach for named entity recognition and relation extraction from large natural language resources like scientific research, news articles and webpages- this approach has both proven very successful in practice with a variety of large corpora and is flexible enough to adjust to the specific content types relevant to the BDG use cases.</p>\n\n<p>The proposed pipelines work by identifying entities that refer to instances from the conceptual BDG model so a crucial part of our discussion involves a theoretical definition of that model and detailing the approach to building, extending and enlarging the model with new facts and new provenance sources. We will also describe the process for building a reliable corpus of data that can be used to develop and evaluate the performance of the various pipelines as well as the proposed structure of the linguistic pipelines themselves.</p>"
  }
}
20
21
views
downloads
All versions This version
Views 2020
Downloads 2121
Data volume 30.9 MB30.9 MB
Unique views 1818
Unique downloads 1919

Share

Cite as