Abstract
We interpret the predictions of any black-box structured input-structured output model around a specific input-output pair. Our method returns an “explanation” consisting of groups of input-output tokens that are causally related. These dependencies are inferred by querying the model with perturbed inputs, generating a graph over tokens from the responses, and solving a partitioning problem to select the most relevant components. We focus the general approach on sequence-to-sequence problems, adopting a variational autoencoder to yield meaningful input perturbations. We test our method across several NLP sequence generation tasks.- Anthology ID:
- D17-1042
- Volume:
- Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
- Month:
- September
- Year:
- 2017
- Address:
- Copenhagen, Denmark
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 412–421
- Language:
- URL:
- https://aclanthology.org/D17-1042
- DOI:
- 10.18653/v1/D17-1042
- Cite (ACL):
- David Alvarez-Melis and Tommi Jaakkola. 2017. A causal framework for explaining the predictions of black-box sequence-to-sequence models. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 412–421, Copenhagen, Denmark. Association for Computational Linguistics.
- Cite (Informal):
- A causal framework for explaining the predictions of black-box sequence-to-sequence models (Alvarez-Melis & Jaakkola, EMNLP 2017)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/D17-1042.pdf