@inproceedings{dcf39485738344c094d3fc3ea564a1af,
title = "Cross-lingual document retrieval using regularized wasserstein distance",
abstract = "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{\textquoteright}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.",
author = "Georgios Balikas and Charlotte Laclau and Ievgen Redko and Amini, \{Massih Reza\}",
note = "Publisher Copyright: {\textcopyright} Springer International Publishing AG, part of Springer Nature 2018.; 40th European Conference on Information Retrieval, ECIR 2018 ; Conference date: 26-03-2018 Through 29-03-2018",
year = "2018",
month = jan,
day = "1",
doi = "10.1007/978-3-319-76941-7\_30",
language = "English",
isbn = "9783319769400",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "398--410",
editor = "Leif Azzopardi and Gabriella Pasi and Allan Hanbury and Benjamin Piwowarski",
booktitle = "Advances in Information Retrieval - 40th European Conference on IR Research, ECIR 2018, Proceedings",
}