Language Resources and Evaluation

, Volume 49, Issue 4, pp 883–905

TweetNorm: a benchmark for lexical normalization of Spanish tweets

  • Iñaki Alegria
  • Nora Aranberri
  • Pere R. Comas
  • Víctor Fresno
  • Pablo Gamallo
  • Lluis Padró
  • Iñaki San Vicente
  • Jordi Turmo
  • Arkaitz Zubiaga
Original Paper

DOI: 10.1007/s10579-015-9315-6

Cite this article as:
Alegria, I., Aranberri, N., Comas, P.R. et al. Lang Resources & Evaluation (2015) 49: 883. doi:10.1007/s10579-015-9315-6

Abstract

The language used in social media is often characterized by the abundance of informal and non-standard writing. The normalization of this non-standard language can be crucial to facilitate the subsequent textual processing and to consequently help boost the performance of natural language processing tools applied to social media text. In this paper we present a benchmark for lexical normalization of social media posts, specifically for tweets in Spanish language. We describe the tweet normalization challenge we organized recently, analyze the performance achieved by the different systems submitted to the challenge, and delve into the characteristics of systems to identify the features that were useful. The organization of this challenge has led to the production of a benchmark for lexical normalization of social media, including an evaluation framework, as well as an annotated corpus of Spanish tweets—TweetNorm_es—, which we make publicly available. The creation of this benchmark and the evaluation has brought to light the types of words that submitted systems did best with, and posits the main shortcomings to be addressed in future work.

Keywords

Lexical normalization Twitter Social media Corpus Evaluation 

Copyright information

© Springer Science+Business Media Dordrecht 2015

Authors and Affiliations

  • Iñaki Alegria
    • 1
  • Nora Aranberri
    • 1
  • Pere R. Comas
    • 2
  • Víctor Fresno
    • 3
  • Pablo Gamallo
    • 4
  • Lluis Padró
    • 2
  • Iñaki San Vicente
    • 5
  • Jordi Turmo
    • 2
  • Arkaitz Zubiaga
    • 6
  1. 1.IXA. UPV/EHUSan SebastianSpain
  2. 2.UPCBarcelonaSpain
  3. 3.UNEDMadridSpain
  4. 4.USCSantiago de CompostelaSpain
  5. 5.ElhuyarUsurbilSpain
  6. 6.University of WarwickCoventryUK