How Useful Are the Machine-Generated Interpretations to General Users? A Human Evaluation on Guessing the Incorrectly Predicted Labels
Citations Over TimeTop 10% of 2020 papers
Abstract
Explaining to users why automated systems make certain mistakes is important and challenging. Researchers have proposed ways to automatically produce interpretations for deep neural network models. However, it is unclear how useful these interpretations are in helping users figure out why they are getting an error. If an interpretation effectively explains to users how the underlying deep neural network model works, people who were presented with the interpretation should be better at predicting the model’s outputs than those who were not. This paper presents an investigation on whether or not showing machine-generated visual interpretations helps users understand the incorrectly predicted labels produced by image classifiers. We showed the images and the correct labels to 150 online crowd workers and asked them to select the incorrectly predicted labels with or without showing them the machine-generated visual interpretations. The results demonstrated that displaying the visual interpretations did not increase, but rather decreased, the average guessing accuracy by roughly 10%.
Related Papers
- → DISKURSUS TAFSIR MAQĀṢIDI(2020)5 cited
- → THE METHOD OF INTERPRETATION ON QS. AL-FATIHAH IN TARJUMAN AL-MUSTAFID BY ABDUL RAUF AS-SINGKILI(2022)3 cited
- → Al-Dakhîl fî al-Tafsîr; Studi Kritis dalam Metodologi Tafsir(2014)1 cited
- → Metodologi Tafsir Mukhtasar(2022)
- → Affection in Interpretation According to Abi Hayyan Al-Andalusi (d. 745 A.H) Through his Interpretation of Al-Bahr Al-Moheet Surat Al-Baqarah as a Model(2023)