@inproceedings{SanguinettiBoscoCassidyetal.2020, author = {Sanguinetti, Manuela and Bosco, Cristina and Cassidy, Lauren and {\c{C}}etinoğlu, {\"O}zlem and Cignarella, Alessandra Teresa and Lynn, Teresa and Rehbein, Ines and Ruppenhofer, Josef and Seddah, Djam{\´e} and Zeldes, Amir}, title = {Treebanking User-Generated Content: A Proposal for a Unified Representation in Universal Dependencies}, booktitle = {Proceedings of the 12th International Conference on Language Resources and Evaluation (LREC), May 11-16, 2020, Palais du Pharo, Marseille, France}, editor = {Calzolari, Nicoletta and B{\´e}chet, Fr{\´e}d{\´e}ric and Blache, Philippe and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\´e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios}, isbn = {979-10-95546-34-4}, url = {http://www.lrec-conf.org/proceedings/lrec2020/index.html\#5240}, pages = {5240 -- 5250}, year = {2020}, abstract = {The paper presents a discussion on the main linguistic phenomena of user-generated texts found in web and social media, and proposes a set of annotation guidelines for their treatment within the Universal Dependencies (UD) framework. 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 paper is twofold: (1) to provide a short, 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 main goal of this paper is to provide a common framework for those teams interested in developing similar resources in UD, thus enabling cross-linguistic consistency, which is a principle that has always been in the spirit of UD.}, subject = {Strukturbaum}, language = {en} }