Towards Faithful Model Explanation in NLP: A Survey

September 22, 2022 ยท The Cartographer ยท ๐Ÿ› Computational Linguistics

๐Ÿ“š THE CARTOGRAPHER: The Cartographer
Survey/review paper โ€” maps the landscape rather than implementing a method.

"No code URL or promise found in abstract"
"Title-pattern auto-detect: Towards Faithful Model Explanation in NLP: A Survey"

Evidence collected by the PWNC Scanner

Authors Qing Lyu, Marianna Apidianaki, Chris Callison-Burch arXiv ID 2209.11326 Category cs.CL: Computation & Language Citations 177 Venue Computational Linguistics Last Checked 7 days ago
Abstract
End-to-end neural Natural Language Processing (NLP) models are notoriously difficult to understand. This has given rise to numerous efforts towards model explainability in recent years. One desideratum of model explanation is faithfulness, i.e. an explanation should accurately represent the reasoning process behind the model's prediction. In this survey, we review over 110 model explanation methods in NLP through the lens of faithfulness. We first discuss the definition and evaluation of faithfulness, as well as its significance for explainability. We then introduce recent advances in faithful explanation, grouping existing approaches into five categories: similarity-based methods, analysis of model-internal structures, backpropagation-based methods, counterfactual intervention, and self-explanatory models. For each category, we synthesize its representative studies, strengths, and weaknesses. Finally, we summarize their common virtues and remaining challenges, and reflect on future work directions towards faithful explainability in NLP.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Computation & Language

๐ŸŒ… ๐ŸŒ… Old Age

Attention Is All You Need

Ashish Vaswani, Noam Shazeer, ... (+6 more)

cs.CL ๐Ÿ› NeurIPS ๐Ÿ“š 166.0K cites 9 years ago