March 19, 2022 Conference paper Open Access

Elaine Zosa; Emanuela Boros; Boshko Koloski; Lidia Pivovarova

JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/cd2d2a03-ab6f-4a8a-b2a8-aa765b369e62/SemEval_2022___28_February_2022___5_pages___EMBEDDIA_at_SemEval_2022_Task_8__Investigating_Sentence__Image__and_Knowledge_Graph_Representations.pdf"
      }, 
      "checksum": "md5:152af77ead089f38cf624d3830cafb3d", 
      "bucket": "cd2d2a03-ab6f-4a8a-b2a8-aa765b369e62", 
      "key": "SemEval_2022___28_February_2022___5_pages___EMBEDDIA_at_SemEval_2022_Task_8__Investigating_Sentence__Image__and_Knowledge_Graph_Representations.pdf", 
      "type": "pdf", 
      "size": 2347635
    }
  ], 
  "owners": [
    58661
  ], 
  "doi": "10.5281/zenodo.6369944", 
  "stats": {
    "version_unique_downloads": 64.0, 
    "unique_views": 111.0, 
    "views": 120.0, 
    "version_views": 120.0, 
    "unique_downloads": 64.0, 
    "version_unique_views": 111.0, 
    "volume": 157291545.0, 
    "version_downloads": 67.0, 
    "downloads": 67.0, 
    "version_volume": 157291545.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.6369944", 
    "conceptdoi": "https://doi.org/10.5281/zenodo.6369943", 
    "bucket": "https://zenodo.org/api/files/cd2d2a03-ab6f-4a8a-b2a8-aa765b369e62", 
    "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.6369943.svg", 
    "html": "https://zenodo.org/record/6369944", 
    "latest_html": "https://zenodo.org/record/6369944", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.6369944.svg", 
    "latest": "https://zenodo.org/api/records/6369944"
  }, 
  "conceptdoi": "10.5281/zenodo.6369943", 
  "created": "2022-03-19T11:16:39.129181+00:00", 
  "updated": "2022-03-25T12:42:46.997763+00:00", 
  "conceptrecid": "6369943", 
  "revision": 3, 
  "id": 6369944, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.6369944", 
    "description": "<p>In this paper, we present the participation of the EMBEDDIA team to the SemEval 2022 Task 8 (Multilingual News Article Similarity). We cover several techniques and propose different methods for finding the multilingual news article similarity by exploring the dataset in its entirety. We take advantage of the textual content of the articles, the provided metadata (e.g., titles, keywords, topics), the translated articles, the images (those that were available), and knowledge graph-based representations for entities and relations present in the articles. We, then, compute the semantic similarity between the different features and predict through regression the similarity scores. Our findings show that, while our researched methods obtained promising results, exploiting the semantic textual similarity with sentence representations is unbeatable. Finally, in the official SemEval 2022 Task 8, we ranked fifth in the overall team ranking cross-lingual results, and second in the English-only results.</p>", 
    "license": {
      "id": "CC-BY-4.0"
    }, 
    "title": "EMBEDDIA at SemEval-2022 Task 8: Investigating Sentence, Image, and Knowledge Graph Representations for Multilingual News Article Similarity", 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "6369943"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "6369944"
          }
        }
      ]
    }, 
    "grants": [
      {
        "code": "770299", 
        "links": {
          "self": "https://zenodo.org/api/grants/10.13039/501100000780::770299"
        }, 
        "title": "NewsEye: A Digital Investigator for Historical Newspapers", 
        "acronym": "NewsEye", 
        "program": "H2020", 
        "funder": {
          "doi": "10.13039/501100000780", 
          "acronyms": [], 
          "name": "European Commission", 
          "links": {
            "self": "https://zenodo.org/api/funders/10.13039/501100000780"
          }
        }
      }, 
      {
        "code": "825153", 
        "links": {
          "self": "https://zenodo.org/api/grants/10.13039/501100000780::825153"
        }, 
        "title": "Cross-Lingual Embeddings for Less-Represented Languages in European News Media", 
        "acronym": "EMBEDDIA", 
        "program": "H2020", 
        "funder": {
          "doi": "10.13039/501100000780", 
          "acronyms": [], 
          "name": "European Commission", 
          "links": {
            "self": "https://zenodo.org/api/funders/10.13039/501100000780"
          }
        }
      }
    ], 
    "communities": [
      {
        "id": "embeddia"
      }, 
      {
        "id": "newseye"
      }
    ], 
    "publication_date": "2022-03-19", 
    "creators": [
      {
        "name": "Elaine Zosa"
      }, 
      {
        "name": "Emanuela Boros"
      }, 
      {
        "name": "Boshko Koloski"
      }, 
      {
        "name": "Lidia Pivovarova"
      }
    ], 
    "meeting": {
      "title": "Proceedings of SemEval-2022 Workshop Task 8"
    }, 
    "access_right": "open", 
    "resource_type": {
      "subtype": "conferencepaper", 
      "type": "publication", 
      "title": "Conference paper"
    }, 
    "related_identifiers": [
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.6369943", 
        "relation": "isVersionOf"
      }
    ]
  }
}