Add COLING reference

README.md

@@ -1,10 +1,8 @@
 # tweet-topic-21-multi
 
-This is a RoBERTa-base model trained on ~124M tweets from January 2018 to December 2021 (see [here](https://huggingface.co/cardiffnlp/twitter-roberta-base-2021-124m)), and finetuned for multi-label topic classification on a corpus of 11,267 [tweets](https://huggingface.co/datasets/cardiffnlp/tweet_topic_multi).
-The original RoBERTa-base model can be found [here](https://huggingface.co/cardiffnlp/twitter-roberta-base-2021-124m) and the original reference paper is [TweetEval](https://github.com/cardiffnlp/tweeteval). This model is suitable for English. 
+This model is based on a [TimeLMs](https://github.com/cardiffnlp/timelms) language model trained on ~124M tweets from January 2018 to December 2021 (see [here](https://huggingface.co/cardiffnlp/twitter-roberta-base-2021-124m)), and finetuned for multi-label topic classification on a corpus of 11,267 [tweets](https://huggingface.co/datasets/cardiffnlp/tweet_topic_multi). This model is suitable for English. 
 
- - Reference Papers: [TimeLMs paper](https://arxiv.org/abs/2202.03829), [TweetTopic](https://arxiv.org/abs/2209.09824). 
-- Git Repo: [TimeLMs official repository](https://github.com/cardiffnlp/timelms).
+ - Reference Paper: [TweetTopic](https://arxiv.org/abs/2209.09824) (COLING 2022). 
 
 <b>Labels</b>: