@article{SanguinettiBoscoCassidyetal.2022,
  author    = {Manuela Sanguinetti and Cristina Bosco and Lauren Cassidy and {\"O}zlem Cetinoglu and Alessandra Teresa Cignarella and Teresa Lynn and Ines Rehbein and Josef Ruppenhofer and Djam{\´e} Seddah and Amir Zeldes},
  title     = {Treebanking user-generated content: a UD based overview of guidelines, corpora and unified recommendations},
  series   = {Language Resources and Evaluation},
  volume    = {57},
  publisher = {Springer},
  address   = {Dordrecht [u.a.]},
  issn      = {1574-0218},
  doi       = {10.1007/s10579-022-09581-9},
  url       = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-110002},
  pages     = {493 -- 544},
  year      = {2022},
  abstract  = {This article presents a discussion on the main linguistic phenomena which cause difficulties in the analysis of user-generated texts found on the web and in social media, and proposes a set of annotation guidelines for their treatment within the Universal Dependencies (UD) framework of syntactic analysis. Given on the one hand the increasing number of treebanks featuring user-generated content, and its somewhat inconsistent treatment in these resources on the other, the aim of this article is twofold: (1) to provide a condensed, though comprehensive, overview of such treebanks—based on available literature—along with their main features and a comparative analysis of their annotation criteria, and (2) to propose a set of tentative UD-based annotation guidelines, to promote consistent treatment of the particular phenomena found in these types of texts. The overarching goal of this article is to provide a common framework for researchers interested in developing similar resources in UD, thus promoting cross-linguistic consistency, which is a principle that has always been central to the spirit of UD.},
  language  = {en}
}