Update README.md

README.md

@@ -7,16 +7,24 @@ In addition, we partially translated 6.1 million sentences from the German Wikip
 If you would like to use our model, please cite our paper:
 
 ```
-@InProceedings{lothritz-EtAl:2022:LREC,
-author = {Lothritz, Cedric and Lebichot, Bertrand and Allix, Kevin and Veiber, Lisa and BISSYANDE, TEGAWENDE and Klein, Jacques and Boytsov, Andrey and Lefebvre, Clément and Goujon, Anne},
-title = {LuxemBERT: Simple and Practical Data Augmentation in Language Model Pre-Training for Luxembourgish},
-booktitle = {Proceedings of the Language Resources and Evaluation Conference},
-month = {June},
-year = {2022},
-address = {Marseille, France},
-publisher = {European Language Resources Association},
-pages = {5080--5089},
-abstract = {Pre-trained Language Models such as BERT have become ubiquitous in NLP where they have achieved state-of-the-art performance in most NLP tasks. While these models are readily available for English and other widely spoken languages, they remain scarce for low-resource languages such as Luxembourgish. In this paper, we present LuxemBERT, a BERT model for the Luxembourgish language that we create using the following approach: we augment the pre-training dataset by considering text data from a closely related language that we partially translate using a simple and straightforward method. We are then able to produce the LuxemBERT model, which we show to be effective for various NLP tasks: it outperforms a simple baseline built with the available Luxembourgish text data as well the multilingual mBERT model, which is currently the only option for transformer-based language models in Luxembourgish. Furthermore, we present datasets for various downstream NLP tasks that we created for this study and will make available to researchers on request.},
-url = {https://aclanthology.org/2022.lrec-1.543}
+@inproceedings{lothritz-etal-2022-luxembert,
+    title = "{L}uxem{BERT}: Simple and Practical Data Augmentation in Language Model Pre-Training for {L}uxembourgish",
+    author = "Lothritz, Cedric  and
+      Lebichot, Bertrand  and
+      Allix, Kevin  and
+      Veiber, Lisa  and
+      Bissyande, Tegawende  and
+      Klein, Jacques  and
+      Boytsov, Andrey  and
+      Lefebvre, Cl{\'e}ment  and
+      Goujon, Anne",
+    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-1.543",
+    pages = "5080--5089",
+    abstract = "Pre-trained Language Models such as BERT have become ubiquitous in NLP where they have achieved state-of-the-art performance in most NLP tasks. While these models are readily available for English and other widely spoken languages, they remain scarce for low-resource languages such as Luxembourgish. In this paper, we present LuxemBERT, a BERT model for the Luxembourgish language that we create using the following approach: we augment the pre-training dataset by considering text data from a closely related language that we partially translate using a simple and straightforward method. We are then able to produce the LuxemBERT model, which we show to be effective for various NLP tasks: it outperforms a simple baseline built with the available Luxembourgish text data as well the multilingual mBERT model, which is currently the only option for transformer-based language models in Luxembourgish. Furthermore, we present datasets for various downstream NLP tasks that we created for this study and will make available to researchers on request.",
 }
 ```