Welcome to the competition for the TweetQA dataset. This task requires model to read a short tweet and a question and outputs a text phrase (does not need to be in the tweet) as the answer. More details can be found in TweetQA website. If you want to show you results on the public leaderboard (tweetqa.github.io), please send your model name (i.e., XXNet), organization or team name (optional) and results to hongwang600@ucsb.edu, and indicate whether external dataset is used or not. Also, please submit a description paper on arxiv, so that we can link that to your results on the leaderboard. Thanks!
In order to match your submissions with the groundtruth, name your submission file as "test_answers.json". The submissions will be evaluated using BLEU-1, METEOR, and ROUGE-L metrics. The data and evaluation script can be downloaded from tweetqa.github.io.
Please indicate your organization and model name when submitting the result. Thanks!
Start: July 20, 2019, midnight
Dec. 31, 2099, midnight
You must be logged in to participate in competitions.
Sign In# | Username | Score |
---|---|---|
1 | LHblack | 0.75 |
2 | PingAnLifeInsuranceAI | 0.73 |
3 | mengqingyang0102 | 0.73 |