Conference paper Open Access

Character-based Neural Embeddings for Tweet Clustering

Nixon, Lyndon; Vakulenko, Svitlana; Lupu, Mihai


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/e7efcab8-655d-4599-a2fa-6748f02283de/character-based-neural.pdf"
      }, 
      "checksum": "md5:41bdd3ee3b54e195236d9845aaf083a2", 
      "bucket": "e7efcab8-655d-4599-a2fa-6748f02283de", 
      "key": "character-based-neural.pdf", 
      "type": "pdf", 
      "size": 188230
    }
  ], 
  "owners": [
    31755
  ], 
  "doi": "10.5281/zenodo.582565", 
  "stats": {
    "version_unique_downloads": 17.0, 
    "unique_views": 27.0, 
    "views": 27.0, 
    "downloads": 17.0, 
    "unique_downloads": 17.0, 
    "version_unique_views": 27.0, 
    "volume": 3199910.0, 
    "version_downloads": 17.0, 
    "version_views": 27.0, 
    "version_volume": 3199910.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.582565", 
    "latest_html": "https://zenodo.org/record/582565", 
    "bucket": "https://zenodo.org/api/files/e7efcab8-655d-4599-a2fa-6748f02283de", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.582565.svg", 
    "html": "https://zenodo.org/record/582565", 
    "latest": "https://zenodo.org/api/records/582565"
  }, 
  "created": "2017-05-23T11:02:57.979544+00:00", 
  "updated": "2017-09-08T08:03:17.418723+00:00", 
  "conceptrecid": "787233", 
  "revision": 5, 
  "id": 582565, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.582565", 
    "description": "<p>In this paper we show how the performance of tweet clustering can be improved by leveraging character-based neural networks. The proposed approach overcomes the limitations related to the vocabulary explosion in the word-based models and allows for the seamless processing of the multilingual content. Our evaluation results and code are available on-line.</p>", 
    "license": {
      "id": "CC-BY-4.0"
    }, 
    "title": "Character-based Neural Embeddings for Tweet Clustering", 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "787233"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "582565"
          }
        }
      ]
    }, 
    "communities": [
      {
        "id": "invid-h2020"
      }
    ], 
    "keywords": [
      "Story Detection, Tweet Clustering, Tweet2vec, Vector Space Model, Character-based Embedding"
    ], 
    "publication_date": "2017-04-03", 
    "creators": [
      {
        "affiliation": "MODUL Technology", 
        "name": "Nixon, Lyndon"
      }, 
      {
        "affiliation": "Vienna University of Economics and Business", 
        "name": "Vakulenko, Svitlana"
      }, 
      {
        "affiliation": "TU Wien", 
        "name": "Lupu, Mihai"
      }
    ], 
    "access_right": "open", 
    "resource_type": {
      "subtype": "conferencepaper", 
      "type": "publication", 
      "title": "Conference paper"
    }
  }
}
27
17
views
downloads
All versions This version
Views 2727
Downloads 1717
Data volume 3.2 MB3.2 MB
Unique views 2727
Unique downloads 1717

Share

Cite as