# Rationalizing Text Matching: Learning Sparse Alignments via Optimal Transport

arXiv: https://arxiv.org/abs/2005.13111 · HTML: https://mlsanity.com/paper/2005.13111/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 May 2020.

## Built on by (most cited first, 20 of 20)

- [Word Alignment by Fine-tuning Embeddings on Parallel Corpora](https://mlsanity.com/paper/2101.08231/) (2021)
- [Can Rationalization Improve Robustness?](https://mlsanity.com/paper/2204.11790/) (2022)
- [Multi-Vector Models with Textual Guidance for Fine-Grained Scientific Document Similarity](https://mlsanity.com/paper/2111.08366/) (2021)
- [SPECTRA: Sparse Structured Text Rationalization](https://mlsanity.com/paper/2109.04552/) (2021)
- [Interpreting Deep Learning Models in Natural Language Processing: A Review](https://mlsanity.com/paper/2110.10470/) (2021)
- [Editable User Profiles for Controllable Text Recommendation](https://mlsanity.com/paper/2304.04250/) (2023)
- [Toward Interpretable Semantic Textual Similarity via Optimal Transport-based Contrastive Sentence Learning](https://mlsanity.com/paper/2202.13196/) (2022)
- [Does External Knowledge Help Explainable Natural Language Inference? Automatic Evaluation vs. Human Ratings](https://mlsanity.com/paper/2109.07833/) (2021)
- [OTExtSum: Extractive Text Summarisation with Optimal Transport](https://mlsanity.com/paper/2204.10086/) (2022)
- [Unbalanced Optimal Transport for Unbalanced Word Alignment](https://mlsanity.com/paper/2306.04116/) (2023)
- [Exploring the Trade-off Between Model Performance and Explanation Plausibility of Text Classifiers Using Human Rationales](https://mlsanity.com/paper/2404.03098/) (2024)
- [Submodular Framework for Structured-Sparse Optimal Transport](https://mlsanity.com/paper/2406.04914/) (2024)
- [Order Constraints in Optimal Transport](https://mlsanity.com/paper/2110.07275/) (2021)
- [Tracking Semantic Change in Slovene: A Novel Dataset and Optimal Transport-Based Distance](https://mlsanity.com/paper/2402.16596/) (2024)
- [Monte Carlo Tree Search for Interpreting Stress in Natural Language](https://mlsanity.com/paper/2204.08105/) (2022)
- [CSSAM:Code Search via Attention Matching of Code Semantics and Structures](https://mlsanity.com/paper/2208.03922/) (2022)
- [Transferring Knowledge via Neighborhood-Aware Optimal Transport for Low-Resource Hate Speech Detection](https://mlsanity.com/paper/2210.09340/) (2022)
- [Sparse Domain Transfer via Elastic Net Regularization](https://mlsanity.com/paper/2405.07489/) (2024)
- [Aligning Multilingual News for Stock Return Prediction](https://mlsanity.com/paper/2510.19203/) (2025)
- [Grammatical Error Correction Evaluation by Optimally Transporting Edit Representation](https://mlsanity.com/paper/2602.05419/) (2026)

## Abstract (arXiv)

Selecting input features of top relevance has become a popular method for building self-explaining models. In this work, we extend this selective rationalization approach to text matching, where the goal is to jointly select and align text pieces, such as tokens or sentences, as a justification for the downstream prediction. Our approach employs optimal transport (OT) to find a minimal cost alignment between the inputs. However, directly applying OT often produces dense and therefore uninterpretable alignments. To overcome this limitation, we introduce novel constrained variants of the OT problem that result in highly sparse alignments with controllable sparsity. Our model is end-to-end differentiable using the Sinkhorn algorithm for OT and can be trained without any alignment annotations. We evaluate our model on the StackExchange, MultiNews, e-SNLI, and MultiRC datasets. Our model achieves very sparse rationale selections with high fidelity while preserving prediction accuracy compared to strong attention baseline models.