output
20172020
most citedInterpretable Credit Application Predictions With Counterfactual Explanations

86 citations

6 papers

cs.CL2020★ 10 cited

A Dataset Independent Set of Baselines for Relation Prediction in Argument Mining

Oana Cocarascu, Elena Cabrio, Serena Villata +1

Argument Mining is the research area which aims at extracting argument components and predicting argumentative relations (i.e.,support and attack) from text. In particular, numerou…

cs.HC2020★ 1 cited

Path Outlines: Browsing Path-Based Summaries of Knowledge Graphs

Marie Destandau, Olivier Corby, Jean-Daniel Fekete +1

Knowledge Graphs have become a ubiquitous technology powering search engines, recommender systems, connected objects, corporate knowledge management and Open Data. They rely on sma…

cs.CL2019★ 2 cited

Love Me, Love Me, Say (and Write!) that You Love Me: Enriching the WASABI Song Corpus with Lyrics Annotations

Michael Fell, Elena Cabrio, Elmahdi Korfed +2

We present the WASABI Song Corpus, a large corpus of songs enriched with metadata extracted from music databases on the Web, and resulting from the processing of song lyrics and fr…

cs.AI2018★ 86 cited

Interpretable Credit Application Predictions With Counterfactual Explanations

Rory Mc Grath, Luca Costabello, Chan Le Van +4

We predict credit applications with off-the-shelf, interchangeable black-box classifiers and we explain single predictions with counterfactual explanations. Counterfactual explanat…

cs.AI2018★ 29 cited

Knowledge-based Transfer Learning Explanation

Jiaoyan Chen, Freddy Lecue, Jeff Z. Pan +2

Machine learning explanation can significantly boost machine learning's application in decision making, but the usability of current methods is limited in human-centric explanation…

cs.AI2017★ 15 cited

Prioritized Norms in Formal Argumentation

Beishui Liao, Nir Oren, Leendert van der Torre +1

To resolve conflicts among norms, various nonmonotonic formalisms can be used to perform prioritized normative reasoning. Meanwhile, formal argumentation provides a way to represen…