loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Ilya S. Smirnov and Ivan P. Yamshchikov

Affiliation: LEYA Lab, Yandex, Higher School of Economics, Russia

Keyword(s): Semantic Similarity, WMD, Word Mover’s Distance, Hyperbolic Space, Poincare Embeddings, Alpha Embeddings.

Abstract: The word mover’s distance (WMD) is a popular semantic similarity metric for two documents. This metric is quite interpretable and reflects the similarity well, but some aspects can be improved. This position paper studies several possible extensions of WMD. We introduce some regularizations of WMD based on a word match and the frequency of words in the corpus as a weighting factor. Besides, we calculate WMD in word vector spaces with non-Euclidean geometry and compare it with the metric in Euclidean space. We validate possible extensions of WMD on six document classification datasets. Some proposed extensions show better results in terms of the k-nearest neighbor classification error than WMD.

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 18.223.119.17

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Smirnov, I. and Yamshchikov, I. (2022). Moving Other Way: Exploring Word Mover Distance Extensions. In Proceedings of the 7th International Conference on Complexity, Future Information Systems and Risk - COMPLEXIS; ISBN 978-989-758-565-4; ISSN 2184-5034, SciTePress, pages 92-97. DOI: 10.5220/0011096900003197

@conference{complexis22,
author={Ilya S. Smirnov. and Ivan P. Yamshchikov.},
title={Moving Other Way: Exploring Word Mover Distance Extensions},
booktitle={Proceedings of the 7th International Conference on Complexity, Future Information Systems and Risk - COMPLEXIS},
year={2022},
pages={92-97},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011096900003197},
isbn={978-989-758-565-4},
issn={2184-5034},
}

TY - CONF

JO - Proceedings of the 7th International Conference on Complexity, Future Information Systems and Risk - COMPLEXIS
TI - Moving Other Way: Exploring Word Mover Distance Extensions
SN - 978-989-758-565-4
IS - 2184-5034
AU - Smirnov, I.
AU - Yamshchikov, I.
PY - 2022
SP - 92
EP - 97
DO - 10.5220/0011096900003197
PB - SciTePress