Clickbait Resolving Challenge

We present a new corpus of clickbait articles annotated by university students along with a corresponding shared task: clickbait articles use a headline or teaser that on purpose hides information from the reader to get them curious to open the article. We therefore propose to construct approaches that can automatically extract the relevant information from such an article, which we call clickbait resolving. This work was accepted to the 13th Language Resources and Evaluation Conference (LREC’22).

Read the paper Download the corpus Participate

Leaderboard

Rank	Approach	ExactMatch	Rouge-2	Rouge-L	Meteor	BLEU-2	BERTScore
1 Jan 17, 2022	T5 aug+fine (Hättasch & Binnig '21)	7.20 / 4.56	8.70 / 6.88	18.46 / 17.02	22.96 / 20.38	9.10 / 6.90	20.89 / 25.23
2 Jan 17, 2022	T5 fine (Hättasch & Binnig '21)	4.55 / 3.42	7.16 / 7.16	15.68 / 15.34	18.91 / 17.90	7.37 / 6.81	15.67 / 21.37
3 Jan 17, 2022	BART SQuADv2 (Hättasch & Binnig '21)	0.38 / 0.38	5.65 / 6.00	10.30 / 10.34	11.64 / 10.89	5.08 / 6.10	4.76 / 12.76
4 Jan 17, 2022	T5 (Hättasch & Binnig '21)	1.89 / 1.14	3.94 / 2.75	9.07 / 8.49	10.74 / 9.52	4.23 / 2.50	7.30 / 11.24

Acknowledgments

We thank Max Doll, Kathrin Ferring, Martin Otterbein, and Jan-Hendrik Schmidt for the countless hours they spent reading hardly bearable texts.

This work has been supported by the German Research Foundation as part of the Research Training Group Adaptive Preparation of Information from Heterogeneous Sources (AIPHES) under grant No. GRK 1994/1, as well as the Federal Ministry of Education and Research (BMBF) and the state of Hesse as part of the NHR Program.

How to cite

This work was accepted to LREC'22. If you built on it, please cite as follows:

@InProceedings{haettasch22clickbait,
  author    = {Hättasch, Benjamin  and  Binnig, Carsten},
  title     = {Know Better – A Clickbait Resolving Challenge},
  booktitle      = {Proceedings of the Language Resources and Evaluation Conference},
  month          = {June},
  year           = {2022},
  address        = {Marseille, France},
  publisher      = {European Language Resources Association},
  pages     = {515--523},
  url       = {https://aclanthology.org/2022.lrec-1.54}
}

Questions & Contributions

Open a Issue in our repository or contact Benjamin Hättasch

This is a project of Data Management Lab @ TU Darmstadt.