Abstract
Selective rationalization aims to produce decisions along with rationales (e.g., text highlights or word alignments between two sentences). Commonly, rationales are modeled as stochastic binary masks, requiring sampling-based gradient estimators, which complicates training and requires careful hyperparameter tuning. Sparse attention mechanisms are a deterministic alternative, but they lack a way to regularize the rationale extraction (e.g., to control the sparsity of a text highlight or the number of alignments). In this paper, we present a unified framework for deterministic extraction of structured explanations via constrained inference on a factor graph, forming a differentiable layer. Our approach greatly eases training and rationale regularization, generally outperforming previous work on what comes to performance and plausibility of the extracted rationales. We further provide a comparative study of stochastic and deterministic methods for rationale extraction for classification and natural language inference tasks, jointly assessing their predictive power, quality of the explanations, and model variability.- Anthology ID:
- 2021.emnlp-main.525
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6534–6550
- Language:
- URL:
- https://preview.aclanthology.org/remove-affiliations/2021.emnlp-main.525/
- DOI:
- 10.18653/v1/2021.emnlp-main.525
- Cite (ACL):
- Nuno M. Guerreiro and André F. T. Martins. 2021. SPECTRA: Sparse Structured Text Rationalization. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6534–6550, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- SPECTRA: Sparse Structured Text Rationalization (Guerreiro & Martins, EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/remove-affiliations/2021.emnlp-main.525.pdf
- Code
- deep-spin/spectra-rationalization + additional community code
- Data
- IMDb Movie Reviews, SNLI, SST