Many information retrieval algorithms rely on the notion of a good distance that allows to efficiently compare objects of different nature. Recently, a new promising metric called Word Mover's Distance was proposed to measure the divergence between text passages. In this paper, we demonstrate that this metric can be extended to incorporate term-weighting schemes and provide more accurate and computationally efficient matching between documents using entropic regularization. We evaluate the benefits of both extensions in the task of cross-lingual document retrieval (CLDR). Our experimental results on eight CLDR problems suggest that the proposed methods achieve remarkable improvements in terms of Mean Reciprocal Rank compared to several baselines.
@article{arxiv.1805.04437,
title = {Cross-lingual Document Retrieval using Regularized Wasserstein Distance},
author = {Georgios Balikas and Charlotte Laclau and Ievgen Redko and Massih-Reza Amini},
journal= {arXiv preprint arXiv:1805.04437},
year = {2018}
}