In this paper, we propose a corpus-level explanation approach, which aims to capture causal relationships between keywords and model predictions.
Apr 24, 2020 · Our concept-based explanation method is built upon a novel Abstraction-Aggregation Network, which can automatically cluster important ...
A corpus-level explanation approach is proposed, which aims to capture causal relationships between keywords and model predictions via learning importance ...
Automatic Corpus-level and Concept-based Explanation for Attention-based Model for Text Classification. - tshi04/ACCE.
Oct 22, 2021 · Our concept-based explanation method is built upon a novel Abstraction-Aggregation Network (AAN), which can automatically cluster important ...
Oct 22, 2021 · Our concept-based explanation method is built upon a novel Abstraction-Aggregation Network (AAN), which can automatically cluster important ...
A Concept-based Abstraction-Aggregation Deep Neural Network for Interpretable Document Classification. Preprint. Full-text available. Apr 2020. Tian ...
Sep 10, 2024 · A Concept-based Abstraction-Aggregation Deep Neural Network for Interpretable Document Classification. CoRR abs/2004.13003 (2020). [i6]. view.
Sep 25, 2019 · we propose a concept-based explanation for DNNs that is both sufficient for prediction (complete) and interpretable.
Missing: Abstraction- Document
Readers: Everyone. A Concept-based Abstraction-Aggregation Deep Neural Network for Interpretable Document Classification · Tian Shi, Xuchao Zhang, Ping Wang ...