ExplainIt!: A Tool for Computing Robust Attributions of DNNs

Lippi, Marco; Antici, Francesco; Brambilla, Gianfranco; Cisbani, E.; Galassi, Andrea; Giansanti, Daniele; Magurano, Fabio; Rosi, Antonella; Ruggeri, Federico; Torroni, Paolo

doi:10.24963/ijcai.2022/853

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2022

2023

Publication Types

Select...

Other1

Article1

Relationship

Self Cite0

Independent2

Authors

Journals

Cited by 2 publications

References 2 publications

(3 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

Neural SDEs for Robust and Explainable Analysis of Electromagnetic Unintended Radiated Emissions

Jha,

Ewetz

et al. 2023

MILCOM 2023 - 2023 IEEE Military Communications Conference (MILCOM)

View full text Add to dashboard Cite

Neural SDEs for Robust and Explainable Analysis of Electromagnetic Unintended Radiated Emissions

Jha,

Ewetz

et al. 2023

MILCOM 2023 - 2023 IEEE Military Communications Conference (MILCOM)

View full text Add to dashboard Cite

Argument mining as rapid screening tool of COVID-19 literature quality: Preliminary evidence

Brambilla

Rosi

Antici

et al. 2022

Front. Public Health

View full text Add to dashboard Cite

BackgroundThe COVID-19 pandemic prompted the scientific community to share timely evidence, also in the form of pre-printed papers, not peer reviewed yet.PurposeTo develop an artificial intelligence system for the analysis of the scientific literature by leveraging on recent developments in the field of Argument Mining.MethodologyScientific quality criteria were borrowed from two selected Cochrane systematic reviews. Four independent reviewers gave a blind evaluation on a 1–5 scale to 40 papers for each review. These scores were matched with the automatic analysis performed by an AM system named MARGOT, which detected claims and supporting evidence for the cited papers. Outcomes were evaluated with inter-rater indices (Cohen's Kappa, Krippendorff's Alpha, s* statistics).ResultsMARGOT performs differently on the two selected Cochrane reviews: the inter-rater indices show a fair-to-moderate agreement of the most relevant MARGOT metrics both with Cochrane and the skilled interval scores, with larger values for one of the two reviews.Discussion and conclusionsThe noted discrepancy could rely on a limitation of the MARGOT system that can be improved; yet, the level of agreement between human reviewers also suggests a different complexity between the two reviews in debating controversial arguments. These preliminary results encourage to expand and deepen the investigation to other topics and a larger number of highly specialized reviewers, to reduce uncertainty in the evaluation process, thus supporting the retraining of AM systems.

show abstract

ExplainIt!: A Tool for Computing Robust Attributions of DNNs

Cited by 2 publications

References 2 publications

Neural SDEs for Robust and Explainable Analysis of Electromagnetic Unintended Radiated Emissions

Neural SDEs for Robust and Explainable Analysis of Electromagnetic Unintended Radiated Emissions

Argument mining as rapid screening tool of COVID-19 literature quality: Preliminary evidence

Contact Info

Product

Resources

About