论文标题
合理化文本匹配：通过最佳运输学习稀疏对齐
Rationalizing Text Matching: Learning Sparse Alignments via Optimal Transport
论文作者
论文摘要
选择顶级相关性的输入功能已成为构建自我解释模型的流行方法。在这项工作中，我们将这种选择性合理化方法扩展到文本匹配，目标是共同选择和对齐文本片，例如令牌或句子，作为下游预测的理由。我们的方法采用最佳运输（OT）来找到投入之间的最小成本对齐。但是，直接应用OT通常会产生密集，因此无法解释。为了克服这一局限性，我们引入了新型OT问题的限制变化，从而导致高度稀疏的可控稀疏性比对。我们的模型使用ot的sndhorn算法端到端可区分，并且可以在没有任何一致注释的情况下进行训练。我们在Stackexchange，Multinews，E-SNLI和Multim数据集上评估了我们的模型。我们的模型以高忠诚度获得了非常稀疏的理由选择，同时与强大的注意力基线模型相比保留了预测准确性。
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.
