Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | CIKM '21 |
| Untertitel | Proceedings of the 30th ACM International Conference on Information & Knowledge Management |
| Herausgeber (Verlag) | Association for Computing Machinery (ACM) |
| Seiten | 4823-4827 |
| Seitenumfang | 5 |
| ISBN (elektronisch) | 9781450384469 |
| Publikationsstatus | Veröffentlicht - 30 Okt. 2021 |
| Veranstaltung | 30th ACM International Conference on Information and Knowledge Management, CIKM 2021 - Virtual, Online, Australien Dauer: 1 Nov. 2021 → 5 Nov. 2021 |
Publikationsreihe
| Name | International Conference on Information and Knowledge Management, Proceedings |
|---|
Abstract
Fact-checking on the Web has become the main mechanism through which we detect the credibility of the news or information. Existing fact-checkers verify the authenticity of the information (support or refute the claim) based on secondary sources of information. However, existing approaches do not consider the problem of model updates due to constantly increasing training data due to user feedback. It is therefore important to conduct user studies to correct models' inference biases and improve the model in a life-long learning manner in the future according to the user feedback. In this paper, we present FaxPlainAC, a tool that gathers user feedback on the output of explainable fact-checking models. FaxPlainAC outputs both the model decision, i.e., whether the input fact is true or not, along with the supporting/refuting evidence considered by the model. Additionally, FaxPlainAC allows for accepting user feedback both on the prediction and explanation. Developed in Python, FaxPlainAC is designed as a modular and easily deployable tool. It can be integrated with other downstream tasks and allowing for fact-checking human annotation gathering and life-long learning.
ASJC Scopus Sachgebiete
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
CIKM '21: Proceedings of the 30th ACM International Conference on Information & Knowledge Management. Association for Computing Machinery (ACM), 2021. S. 4823-4827 (International Conference on Information and Knowledge Management, Proceedings).
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - FaxPlainAC
T2 - 30th ACM International Conference on Information and Knowledge Management, CIKM 2021
AU - Zhang, Zijian
AU - Rudra, Koustav
AU - Anand, Avishek
N1 - Funding Information: Acknowledgement: Funding for this project was in part provid-edby the European Union’s Horizon 2020 research and innovation program under grant agreement No 832921 and No 871042.
PY - 2021/10/30
Y1 - 2021/10/30
N2 - Fact-checking on the Web has become the main mechanism through which we detect the credibility of the news or information. Existing fact-checkers verify the authenticity of the information (support or refute the claim) based on secondary sources of information. However, existing approaches do not consider the problem of model updates due to constantly increasing training data due to user feedback. It is therefore important to conduct user studies to correct models' inference biases and improve the model in a life-long learning manner in the future according to the user feedback. In this paper, we present FaxPlainAC, a tool that gathers user feedback on the output of explainable fact-checking models. FaxPlainAC outputs both the model decision, i.e., whether the input fact is true or not, along with the supporting/refuting evidence considered by the model. Additionally, FaxPlainAC allows for accepting user feedback both on the prediction and explanation. Developed in Python, FaxPlainAC is designed as a modular and easily deployable tool. It can be integrated with other downstream tasks and allowing for fact-checking human annotation gathering and life-long learning.
AB - Fact-checking on the Web has become the main mechanism through which we detect the credibility of the news or information. Existing fact-checkers verify the authenticity of the information (support or refute the claim) based on secondary sources of information. However, existing approaches do not consider the problem of model updates due to constantly increasing training data due to user feedback. It is therefore important to conduct user studies to correct models' inference biases and improve the model in a life-long learning manner in the future according to the user feedback. In this paper, we present FaxPlainAC, a tool that gathers user feedback on the output of explainable fact-checking models. FaxPlainAC outputs both the model decision, i.e., whether the input fact is true or not, along with the supporting/refuting evidence considered by the model. Additionally, FaxPlainAC allows for accepting user feedback both on the prediction and explanation. Developed in Python, FaxPlainAC is designed as a modular and easily deployable tool. It can be integrated with other downstream tasks and allowing for fact-checking human annotation gathering and life-long learning.
KW - data gathering
KW - fact-checking
KW - human-in-the-loop machine learning
KW - interpretable machine learning
UR - http://www.scopus.com/inward/record.url?scp=85119204381&partnerID=8YFLogxK
U2 - 10.48550/arXiv.2110.10144
DO - 10.48550/arXiv.2110.10144
M3 - Conference contribution
AN - SCOPUS:85119204381
T3 - International Conference on Information and Knowledge Management, Proceedings
SP - 4823
EP - 4827
BT - CIKM '21
PB - Association for Computing Machinery (ACM)
Y2 - 1 November 2021 through 5 November 2021
ER -