Update README.md

README.md

@@ -84,12 +84,19 @@ We are working on integrating this preprocessing step into a Tokenizer within `t
 If you use *RoBERTuito*, please cite our paper:
 
 ```bibtex
-@misc{perez2021robertuito,
-      title={RoBERTuito: a pre-trained language model for social media text in Spanish},
-      author={Juan Manuel Pérez and Damián A. Furman and Laura Alonso Alemany and Franco Luque},
-      year={2021},
-      eprint={2111.09453},
-      archivePrefix={arXiv},
-      primaryClass={cs.CL}
+@inproceedings{perez-etal-2022-robertuito,
+    title = "{R}o{BERT}uito: a pre-trained language model for social media text in {S}panish",
+    author = "P{\'e}rez, Juan Manuel  and
+      Furman, Dami{\'a}n Ariel  and
+      Alonso Alemany, Laura  and
+      Luque, Franco M.",
+    booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
+    month = jun,
+    year = "2022",
+    address = "Marseille, France",
+    publisher = "European Language Resources Association",
+    url = "https://aclanthology.org/2022.lrec-1.785",
+    pages = "7235--7243",
+    abstract = "Since BERT appeared, Transformer language models and transfer learning have become state-of-the-art for natural language processing tasks. Recently, some works geared towards pre-training specially-crafted models for particular domains, such as scientific papers, medical documents, user-generated texts, among others. These domain-specific models have been shown to improve performance significantly in most tasks; however, for languages other than English, such models are not widely available. In this work, we present RoBERTuito, a pre-trained language model for user-generated text in Spanish, trained on over 500 million tweets. Experiments on a benchmark of tasks involving user-generated text showed that RoBERTuito outperformed other pre-trained language models in Spanish. In addition to this, our model has some cross-lingual abilities, achieving top results for English-Spanish tasks of the Linguistic Code-Switching Evaluation benchmark (LinCE) and also competitive performance against monolingual models in English Twitter tasks. To facilitate further research, we make RoBERTuito publicly available at the HuggingFace model hub together with the dataset used to pre-train it.",
 }
 ```