TWEETQA: A Social Media Focused Question Answering Dataset
This dataset addresses the problem of automated question answering for real-time social media content, which is incremental as it extends QA to a new data type but does not propose a novel method.
The authors introduced TWEETQA, the first large-scale question answering dataset focused on social media text, specifically tweets used by journalists, and found that existing neural models, including fine-tuned BERT, perform poorly compared to human performance, highlighting a gap in QA systems for this domain.
With social media becoming increasingly pop-ular on which lots of news and real-time eventsare reported, developing automated questionanswering systems is critical to the effective-ness of many applications that rely on real-time knowledge. While previous datasets haveconcentrated on question answering (QA) forformal text like news and Wikipedia, wepresent the first large-scale dataset for QA oversocial media data. To ensure that the tweetswe collected are useful, we only gather tweetsused by journalists to write news articles. Wethen ask human annotators to write questionsand answers upon these tweets. Unlike otherQA datasets like SQuAD in which the answersare extractive, we allow the answers to be ab-stractive. We show that two recently proposedneural models that perform well on formaltexts are limited in their performance when ap-plied to our dataset. In addition, even the fine-tuned BERT model is still lagging behind hu-man performance with a large margin. Our re-sults thus point to the need of improved QAsystems targeting social media text.