Optimal Transport-based Alignment of Learned Character Representations for String Similarity
This work addresses string similarity for record linkage and entity resolution, presenting a novel method with strong gains but is incremental in combining existing techniques.
The authors tackled the problem of string similarity for alias detection by developing STANCE, a model that encodes characters, aligns them via optimal transport, and scores with a CNN, achieving state-of-the-art performance on four out of five new datasets and improving cross-document coreference by 2.8 points in B^3 F1.
String similarity models are vital for record linkage, entity resolution, and search. In this work, we present STANCE --a learned model for computing the similarity of two strings. Our approach encodes the characters of each string, aligns the encodings using Sinkhorn Iteration (alignment is posed as an instance of optimal transport) and scores the alignment with a convolutional neural network. We evaluate STANCE's ability to detect whether two strings can refer to the same entity--a task we term alias detection. We construct five new alias detection datasets (and make them publicly available). We show that STANCE or one of its variants outperforms both state-of-the-art and classic, parameter-free similarity models on four of the five datasets. We also demonstrate STANCE's ability to improve downstream tasks by applying it to an instance of cross-document coreference and show that it leads to a 2.8 point improvement in B^3 F1 over the previous state-of-the-art approach.