SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2211.09732 · EMNLP · 2022

Extending Logic Explained Networks to Text Classification

Pietro Barbiero, Davide Buffelli, Gabriele Ciravegna, Francesco Giannini, Pietro Lio, Rishabh Jain

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recently, Logic Explained Networks (LENs) have been proposed as explainable-by-design neural models providing logic explanations for their predictions. However, these models have only been applied to vision and tabular data, and they mostly favour the generation of global explanations, while local ones tend to be noisy and verbose. For these reasons, we propose LEN p , improving local explanations by perturbing input words, and we test it on text classification. Our results show that (i) LEN p provides better local explanations than LIME in terms of sensitivity and faithfulness, and (ii) logic explanations are more useful and user-friendly than feature scoring provided by LIME as attested by a human survey.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2211.09732")
get_code_for_paper("2211.09732")
have("2211.09732")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2211.09732.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2211.09732.svg)](https://syntology.ai/paper/2211.09732)

Connect an agent — have() is free.