ITU

MultiLexNorm: A Shared Task on Multilingual Lexical Normalization

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

  • Rob van der Goot
  • Alan Ramponi
  • Arkaitz Zubiaga
  • Barbara Plank
  • Benjamin Muller
  • Iñaki San Vicente Roncal
  • Nikola Ljubešic´
  • Özlem Çetinoğlu
  • Rahmad Mahendra
  • Talha Çolakoglu
  • Timothy Baldwin
  • Tommaso Caselli
  • Wladimir Sidorenko

View graph of relations

Lexical normalization is the task of transforming an utterance into its standardized form. This task is beneficial for downstream analysis, as it provides a way to harmonize (often spontaneous) linguistic variation. Such variation is typical for social media on which information is shared in a multitude of ways, including diverse languages and code-switching. Since the seminal work of Han and Baldwin (2011) a decade ago, lexical normalization has attracted attention in English and multiple other languages. However, there exists a lack of a common benchmark for comparison of systems across languages with a homogeneous data and evaluation setup. The MultiLexNorm shared task sets out to fill this gap. We provide the largest publicly available multilingual lexical normalization benchmark including 13 language variants. We propose a homogenized evaluation setup with both intrinsic and extrinsic evaluation. As extrinsic evaluation, we use dependency parsing and part-of-speech tagging with adapted evaluation metrics (a-LAS, a-UAS, and a-POS) to account for alignment discrepancies. The shared task hosted at W-NUT 2021 attracted 9 participants and 18 submissions. The results show that neural normalization systems outperform the previous state-of-the-art system by a large margin. Downstream parsing and part-of-speech tagging performance is positively affected but to varying degrees, with improvements of up to 1.72 a-LAS, 0.85 a-UAS, and 1.54 a-POS for the winning system.
Original languageEnglish
Title of host publicationProceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)
Number of pages16
PublisherAssociation for Computational Linguistics
Publication dateNov 2021
Pages493–509
Publication statusPublished - Nov 2021
EventSeventh Workshop on Noisy User-generated Text (W-NUT 2021) -
Duration: 11 Nov 202111 Nov 2021
http://noisy-text.github.io/2021/

Conference

ConferenceSeventh Workshop on Noisy User-generated Text (W-NUT 2021)
Periode11/11/202111/11/2021
Internetadresse

ID: 86422562