Elamur Research⌕
☰
home / papers / 2021 / Overview of the CLEF-2019 CheckThat!: Automatic Identification and Verification of Claims

Overview of the CLEF-2019 CheckThat!: Automatic Identification and Verification of Claims

Summary

The CheckThat! lab at CLEF 2019 is the second edition of a shared evaluation campaign on automated fact-checking. It splits verification into two pipeline stages and evaluates each one separately. Task 1 (English) asks systems to score every sentence of a transcribed political debate, speech or press conference so that the claims most deserving a fact-check rise to the top. The gold standard follows the choices of factcheck.org. Task 2 (Arabic) starts from a claim and a set of retrieved Web pages. Systems must rank those pages by usefulness, grade their usefulness, extract useful passages, and finally predict whether the claim is true.

The organizers extended the 2018 English corpus into CT19-T1 and built the Arabic CT19-T2 from scratch, using a commercial search engine together with in-house and crowd annotators. Ranking was scored with MAP and nDCG, and classification with F1. Fourteen teams took part, up from nine the year before. In Task 1, neural networks and logistic regression led the results. In Task 2, learning-to-rank won subtask A and various classifiers led the other subtasks. All data and scorers are public, which makes the lab a reusable benchmark for check-worthiness and evidence-based verification.

Key points

  • Participation: 47 teams registered, 14 submitted, and 57 runs were filed in total. This is about a 55% rise over 2018.
  • CT19-T1 has 16,421 training sentences, of which 433 are check-worthy. The test set has 7,079 sentences with 110 check-worthy. New test material came from 3 press conferences, 6 speeches, 6 debates and 1 post.
  • Labels are assigned at sentence level:
    • A partly checked sentence counts as fully positive.
    • Multi-sentence claims mark every sentence they cover.
    • Repeated mentions of a checked claim are all marked.
    • Some labels were moved by hand to a neighbouring sentence.
  • Team Copenhagen won Task 1 with an LSTM over dual token embeddings, combining domain-specific word vectors with syntactic dependencies. The network was pre-trained on earlier Trump/Clinton debates, weakly supervised with ClaimBuster, and trained with a contrastive ranking loss. Context-window models did not beat sentence-in-isolation models.
  • Subtask 2D (veracity) ran in two cycles, without and then with gold page-usefulness labels. In cycle 2 the top macro-F1 was 0.62 (UPV-UMA), against a majority baseline of 0.34. Cycle 1 had only one valid run (F1 0.48).

Interesting ideas

  • I1. Each pipeline stage (ranking, grading, passage extraction, verdict) gets its own dataset and metric, so teams can compete on one block, and each block can be compared fairly. — For Mova (learn): Score each stage of text → tree → frames → world → answer against its own gold, so a regression can be traced to the exact step that caused it.
  • I2. Subtask D was run twice, once blind and once with gold usefulness labels for the upstream step. This shows how much downstream accuracy is lost to errors earlier in the pipeline. — For Mova (answer): Run the readers on gold UD trees and gold frames versus predicted ones, to measure how much of each test failure comes from parsing rather than reasoning.
  • I3. A trivial baseline for passage usefulness, based only on the passage's position in the page, nearly matched the submitted systems. This exposes how much the task rewards shallow cues. — For Mova (learn): Add position-only and majority-class negative controls to every evaluation, so that a stage which only exploits layout or frequency is caught early.
  • I4. When one mention of a claim was checked, every repetition and every sentence the claim spans was labelled too. This keeps the gold data consistent across mentions. — For Mova (frames): Coreference and claim-repeat linking could spread a frame's status (asserted, disputed, checked) to all its mentions in the world of the text.
  • I5. The winning system mixed syntactic-dependency embeddings with word embeddings and used an existing tool (ClaimBuster) as a weak supervisor. — For Mova (learn): Treat an external classifier as one more silver witness next to the parsers, and keep dependency structure as an explicit, inspectable signal rather than bag-of-words features.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Cited by

8 papers of our library cite it (of the 140884 whose bibliographies we read); 1 of them have a page here, 7 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2109.15118 · arXiv 2109.15118

@misc{elsayed2021overview,
  title = {{Overview of the CLEF-2019 CheckThat!: Automatic Identification and Verification of Claims}},
  author = {Elsayed, Tamer and Nakov, Preslav and Barron-Cedeno, Alberto and Hasanain, Maram and Suwaileh, Reem and Martino, Giovanni Da San and Atanasova, Pepa},
  year = {2021},
  doi = {10.48550/arxiv.2109.15118},
  eprint = {2109.15118},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2109.15118}
}

References

47 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Altun, B., Kutlu, M.: TOBB-ETU at CLEF 2019: Prioritizing claims based on check-worthiness. In: CLEF 2019 Working Notes. Working Notes of CLEF 2019 - Conference and Labs of the Evaluation Forum. CEUR Workshop Proceedings, CEUR-WS.org, Lugano, Switzerland (2019) find
  2. Atanasova, P., Màrquez, L., Barrón-Cedeño, A., Elsayed, T., Suwaileh, R., Zaghouani, W., Kyuchukov, S., Da San Martino, G., Nakov, P.: Overview of the CLEF-2018 CheckThat! Lab on automatic identification and verification of political claims, Task 1: Check-worthiness. In: Cappellato, L., Ferro, N., Nie, J.Y., Soulier, L. (eds.) CLEF 2018 Working Notes. Working Notes of CLEF 2018 - Conference and Labs of the Evaluation Forum. CEUR Workshop Proceedings, CEUR-WS.org, Avignon, France (2018) find
  3. Atanasova, P., Nakov, P., Màrquez, L., Barrón-Cedeño, A., Karadzhov, G., Mihaylova, T., Mohtarami, M., Glass, J.: Automatic fact-checking using context and discourse information. J. Data and Information Quality 11(3), 12:1–12:27 (May 2019) find
  4. Ba, M.L., Berti-Equille, L., Shah, K., Hammady, H.M.: VERA: A platform for veracity estimation over web data. In: Proceedings of the 25th International Conference Companion on World Wide Web. pp. 159–162. WWW ’16 (2016) find
  5. Baly, R., Mohtarami, M., Glass, J., Màrquez, L., Moschitti, A., Nakov, P.: Integrating stance detection and fact checking in a unified corpus. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. pp. 21–27. NAACL-HLT ’18, New Orleans, Louisiana, USA (2018) find our card
  6. Barrón-Cedeño, A., Elsayed, T., Suwaileh, R., Màrquez, L., Atanasova, P., Zaghouani, W., Kyuchukov, S., Da San Martino, G., Nakov, P.: Overview of the CLEF-2018 CheckThat! Lab on automatic identification and verification of political claims, Task 2: Factuality. In: Cappellato, L., Ferro, N., Nie, J.Y., Soulier, L. (eds.) CLEF 2018 Working Notes. Working Notes of CLEF 2018 - Conference and Labs of the Evaluation Forum. CEUR Workshop Proceedings, CEUR-WS.org, Avignon, France (2018) find
  7. Castillo, C., Mendoza, M., Poblete, B.: Information credibility on Twitter. In: Proceedings of the 20th International Conference on World Wide Web. pp. 675– 684. WWW ’11, Hyderabad, India (2011) find
  8. Cer, D., Yang, Y., Kong, S.Y., Hua, N., Limtiaco, N., John, R.S., Constant, N., Guajardo-Cespedes, M., Yuan, S., Tar, C., et al.: Universal sentence encoder. arXiv preprint arXiv:1803.11175 (2018) ↗ our card
  9. Coca, L., Cusmuliuc, C.G., Iftene, A.: CheckThat! 2019 UAICS. In: CLEF 2019 Working Notes. Working Notes of CLEF 2019 - Conference and Labs of the Evaluation Forum. CEUR Workshop Proceedings, CEUR-WS.org, Lugano, Switzerland (2019) find
  10. Dhar, R., Dutta, S., Das, D.: A hybrid model to rank sentences for check-worthiness. In: CLEF 2019 Working Notes. Working Notes of CLEF 2019 - Conference and Labs of the Evaluation Forum. CEUR Workshop Proceedings, CEUR-WS.org, Lugano, Switzerland (2019) find
  11. Elsayed, T., Nakov, P., Barrón-Cedeño, A., Hasanain, M., Suwaileh, R., Da San Martino, G., Atanasova, P.: CheckThat! at CLEF 2019: Automatic identification and verification of claims. In: Azzopardi, L., Stein, B., Fuhr, N., Mayr, P., Hauff, C., Hiemstra, D. (eds.) Advances in Information Retrieval. pp. 309–315. Springer International Publishing (2019) find
  12. Favano, L., Carman, M., Lanzi, P.: TheEarthIsFlat’s submission to CLEF’19 CheckThat! challenge. In: CLEF 2019 Working Notes. Working Notes of CLEF 2019 - Conference and Labs of the Evaluation Forum. CEUR Workshop Proceedings, CEUR-WS.org, Lugano, Switzerland (2019) find
  13. Gasior, J., Przyby la, P.: The IPIPAN team participation in the check-worthiness task of the CLEF2019 CheckThat! Lab. In: CLEF 2019 Working Notes. Working Notes of CLEF 2019 - Conference and Labs of the Evaluation Forum. CEUR Workshop Proceedings, CEUR-WS.org, Lugano, Switzerland (2019) find
  14. Gencheva, P., Nakov, P., Màrquez, L., Barrón-Cedeño, A., Koychev, I.: A context-aware approach for detecting worth-checking claims in political debates. In: Proceedings of the International Conference Recent Advances in Natural Language Processing. pp. 267–276. RANLP ’17, Varna, Bulgaria (2017) find
  15. Ghanem, B., Glavaš, G., Giachanou, A., Ponzetto, S., Rosso, P., Rangel, F.: UPV-UMA at CheckThat! Lab: Verifying Arabic claims using cross lingual approach. In: CLEF 2019 Working Notes. Working Notes of CLEF 2019 - Conference and Labs of the Evaluation Forum. CEUR Workshop Proceedings, CEUR-WS.org, Lugano, Switzerland (2019) find
  16. Hansen, C., Hansen, C., Alstrup, S., Grue Simonsen, J., Lioma, C.: Neural check-worthiness ranking with weak supervision: Finding sentences for fact-checking. In: Companion Proceedings of the 2019 World Wide Web Conference. pp. 994–1000. WWW ’19, San Francisco, USA (2019) find
  17. Hansen, C., Hansen, C., Simonsen, J., Lioma, C.: Neural weakly supervised fact check-worthiness detection with contrastive sampling-based ranking loss. In: CLEF 2019 Working Notes. Working Notes of CLEF 2019 - Conference and Labs of the Evaluation Forum. CEUR Workshop Proceedings, CEUR-WS.org, Lugano, Switzerland (2019) find
  18. Haouari, F., Ali, Z., Elsayed, T.: bigIR at CLEF 2019: Automatic verification of Arabic claims over the web. In: CLEF 2019 Working Notes. Working Notes of CLEF 2019 - Conference and Labs of the Evaluation Forum. CEUR Workshop Proceedings, CEUR-WS.org, Lugano, Switzerland (2019) find
  19. Hardalov, M., Koychev, I., Nakov, P.: In search of credible news. In: Proceedings of the 17th International Conference on Artificial Intelligence: Methodology, Systems, and Applications. pp. 172–180. AIMSA ’16, Varna, Bulgaria (2016) find
  20. Hassan, N., Li, C., Tremayne, M.: Detecting check-worthy factual claims in presidential debates. In: Proceedings of the 24th ACM International Conference on Information and Knowledge Management. pp. 1835–1838. CIKM ’15, Melbourne, Australia (2015) find
  21. Howard, J., Ruder, S.: Universal language model fine-tuning for text classification. arXiv preprint arXiv:1801.06146 (2018) ↗
  22. Jaradat, I., Gencheva, P., Barrón-Cedeño, A., Màrquez, L., Nakov, P.: ClaimRank: Detecting check-worthy claims in Arabic and English. In: Proceedings of the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics. pp. 26–30. NAACL-HLT ’18, New Orleans, Louisiana, USA (2018) find
  23. Järvelin, K., Kekäläinen, J.: Cumulated gain-based evaluation of IR techniques. ACM Transactions on Information Systems (TOIS) 20(4), 422–446 (2002) find
  24. Karadzhov, G., Gencheva, P., Nakov, P., Koychev, I.: We built a fake news & clickbait filter: What happened next will blow your mind! In: Proceedings of the 2017 International Conference on Recent Advances in Natural Language Processing. pp. 334–343. RANLP ’17, Varna, Bulgaria (2017) find
  25. Karadzhov, G., Nakov, P., Màrquez, L., Barrón-Cedeño, A., Koychev, I.: Fully automated fact checking using external sources. In: Proceedings of the International Conference on Recent Advances in Natural Language Processing. pp. 344–353. RANLP ’17, Varna, Bulgaria (2017) find
  26. Ma, J., Gao, W., Mitra, P., Kwon, S., Jansen, B.J., Wong, K.F., Cha, M.: Detecting rumors from microblogs with recurrent neural networks. In: Proceedings of the 25th International Joint Conference on Artificial Intelligence. pp. 3818–3824. IJCAI ’16, New York, New York, USA (2016) find
  27. Manning, C.D., Raghavan, P., Schütze, H.: Introduction to Information Retrieval. Cambridge University Press, New York, NY, USA (2008) find
  28. Mihaylova, T., Karadzhov, G., Atanasova, P., Baly, R., Mohtarami, M., Nakov, P.: SemEval-2019 task 8: Fact checking in community question answering forums. In: Proceedings of the 13th International Workshop on Semantic Evaluation. pp. 860–869. SemEval ’19, Minneapolis, Minnesota, USA (2019) find
  29. Mihaylova, T., Nakov, P., Màrquez, L., Barrón-Cedeño, A., Mohtarami, M., Karadjov, G., Glass, J.: Fact checking in community forums. In: Proceedings of the 33rd AAAI Conference on Artificial Intelligence. pp. 5309–5316. AAAI ’18, New Orleans, Louisiana, USA (2018) find
  30. Mikolov, T., Yih, W.T., Zweig, G.: Linguistic regularities in continuous space word representations. In: Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. pp. 746–751. NAACL-HLT ’13, Atlanta, Georgia, USA (2013) find our card
  31. Mohtaj, S., Himmelsbach, T., Woloszyn, V., Möller, S.: The TU-Berlin team participation in the check-worthiness task of the CLEF-2019 CheckThat! Lab. In: CLEF 2019 Working Notes. Working Notes of CLEF 2019 - Conference and Labs of the Evaluation Forum. CEUR Workshop Proceedings, CEUR-WS.org, Lugano, Switzerland (2019) find
  32. Mukherjee, S., Weikum, G.: Leveraging joint interactions for credibility analysis in news communities. In: Proceedings of the 24th ACM International on Conference on Information and Knowledge Management. pp. 353–362. CIKM ’15, Melbourne, Australia (2015) find
  33. Nakov, P., Barrón-Cedeño, A., Elsayed, T., Suwaileh, R., Màrquez, L., Zaghouani, W., Atanasova, P., Kyuchukov, S., Da San Martino, G.: Overview of the CLEF-2018 CheckThat! Lab on automatic identification and verification of political claims. In: Bellot, P., Trabelsi, C., Mothe, J., Murtagh, F., Yun Nie, J., Soulier, L., Sanjuan, E., Cappellato, L., Ferro, N. (eds.) Proceedings of the Ninth International Conference of the CLEF Association: Experimental IR Meets Multilinguality, Multimodality, and Interaction. Lecture Notes in Computer Science, Springer, Avignon, France (September 2018) find
  34. Nguyen, A.T., Kharosekar, A., Lease, M., Wallace, B.: An interpretable joint graphical model for fact-checking from crowds. In: Proceedings of the 32nd AAAI Conference on Artificial Intelligence. pp. 1511–1518. AAAI ’18, New Orleans, LA, USA (2018) find
  35. Nie, Y., Chen, H., Bansal, M.: Combining fact extraction and verification with neural semantic matching networks. In: Proceedings of the 33rd AAAI Conference on Artificial Intelligence. AAAI ’19, Honolulu, Hawaii, USA (2019) find
  36. Popat, K., Mukherjee, S., Strötgen, J., Weikum, G.: Credibility assessment of textual claims on the web. In: Proceedings of the 25th ACM International Conference on Information and Knowledge Management. pp. 2173–2178. CIKM ’16, Indianapolis, Indiana, USA (2016) find
  37. Popat, K., Mukherjee, S., Yates, A., Weikum, G.: DeClarE: Debunking fake news and false claims using evidence-aware deep learning. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. pp. 22–32. EMNLP ’18, Brussels, Belgium (2018) find our card
  38. Rubin, V.L., Chen, Y., Conroy, N.J.: Deception detection for news: three types of fakes. In: Proceedings of the 78th ASIS&T Annual Meeting: Information Science with Impact: Research in and for the Community. p. 83. American Society for Information Science (2015) find
  39. Shu, K., Sliva, A., Wang, S., Tang, J., Liu, H.: Fake news detection on social media: A data mining perspective. ACM SIGKDD Explorations Newsletter 19(1), 22–36 (2017) find
  40. Su, T., Macdonald, C., Ounis, I.: Entity detection for check-worthiness prediction: Glasgow Terrier at CLEF CheckThat! 2019. In: CLEF 2019 Working Notes. Working Notes of CLEF 2019 - Conference and Labs of the Evaluation Forum. CEUR Workshop Proceedings, CEUR-WS.org, Lugano, Switzerland (2019) find
  41. Thorne, J., Vlachos, A., Christodoulopoulos, C., Mittal, A.: FEVER: a large-scale dataset for Fact Extraction and VERification. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. pp. 809–819. NAACL-HLT ’18, New Orleans, LA, USA (2018) find our card
  42. Touahri, I., Mazroui, A.: Automatic identification and verification of political claims. In: CLEF 2019 Working Notes. Working Notes of CLEF 2019 - Conference and Labs of the Evaluation Forum. CEUR Workshop Proceedings, CEUR-WS.org, Lugano, Switzerland (2019) find
  43. Yasser, K., Kutlu, M., Elsayed, T.: Re-ranking web search results for better fact-checking: A preliminary study. In: Proceedings of 27th ACM International Conference on Information and Knowledge Management. pp. 1783–1786. CIKM ’19, Turin, Italy (2018) find
  44. Yoneda, T., Mitchell, J., Welbl, J., Stenetorp, P., Riedel, S.: UCL machine reading group: Four factor framework for fact finding (HexaF). In: Proceedings of the First Workshop on Fact Extraction and VERification. pp. 97–102. FEVER ’18, Brussels, Belgium (2018) find
  45. Zhu, G., Iglesias, C.A.: Computing semantic similarity of concepts in knowledge graphs. IEEE Transactions on Knowledge and Data Engineering 29(1), 72–85 (2016) find
  46. Zhu, G., Iglesias Fernandez, C.A.: Sematch: semantic entity search from knowledge graph. In: Joint Proceedings of the 1st International Workshop on Summarizing and Presenting Entities and Ontologies and the 3rd International Workshop on Human Semantic Web Interfaces. SumPre-HSWI@ESWC ’2015, Portorož, Slovenia (2015) find
  47. Zubiaga, A., Liakata, M., Procter, R., Hoi, G.W.S., Tolmie, P.: Analysing how people orient to and spread rumours in social media by looking at conversational threads. PloS one 11(3), e0150989 (2016) find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/elsayed-2021-overview-clef-2019-checkthat-automatic/