ProtoTEx: Explaining Model Decisions with Prototype Tensors

Anubrata Das, Chitrank Gupta, Venelin Kovatchev, Matthew Lease, Junyi Jessy Li


Abstract
We present ProtoTEx, a novel white-box NLP classification architecture based on prototype networks (Li et al., 2018). ProtoTEx faithfully explains model decisions based on prototype tensors that encode latent clusters of training examples. At inference time, classification decisions are based on the distances between the input text and the prototype tensors, explained via the training examples most similar to the most influential prototypes. We also describe a novel interleaved training algorithm that effectively handles classes characterized by ProtoTEx indicative features. On a propaganda detection task, ProtoTEx accuracy matches BART-large and exceeds BERTlarge with the added benefit of providing faithful explanations. A user study also shows that prototype-based explanations help non-experts to better recognize propaganda in online news.
Anthology ID:
2022.acl-long.213
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2986–2997
Language:
URL:
https://aclanthology.org/2022.acl-long.213
DOI:
10.18653/v1/2022.acl-long.213
Bibkey:
Cite (ACL):
Anubrata Das, Chitrank Gupta, Venelin Kovatchev, Matthew Lease, and Junyi Jessy Li. 2022. ProtoTEx: Explaining Model Decisions with Prototype Tensors. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2986–2997, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
ProtoTEx: Explaining Model Decisions with Prototype Tensors (Das et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.213.pdf
Code
 anubrata/prototex