Add paper

README.md

@@ -19,7 +19,7 @@ pipeline_tag: text-classification
 
 This model is based on  [cardiffnlp/twitter-xlm-roberta-large-2022](https://huggingface.co/cardiffnlp/twitter-xlm-roberta-large-2022) language model and isfinetuned for multi-label topic classification in English, Spanish, Japanese, and Greek.
 
-The models is trained using [TweetTopic](https://huggingface.co/datasets/cardiffnlp/tweet_topic_multi) and [X-Topic](https://huggingface.co/datasets/cardiffnlp/tweet_topic_multilingual) datasets.
+The models is trained using [TweetTopic](https://huggingface.co/datasets/cardiffnlp/tweet_topic_multi) and [X-Topic](https://huggingface.co/datasets/cardiffnlp/tweet_topic_multilingual) datasets (see main [EMNLP 2024 reference paper](https://arxiv.org/abs/2410.03075).