Locality Preserving Loss to Align Vector Spaces

Thumbnail Image

Files

2004.03734.pdf (545.12 KB)

Links to Files

https://arxiv.org/abs/2004.03734

Permanent Link

http://hdl.handle.net/11603/18590

Collections

UMBC Computer Science and Electrical Engineering Department
UMBC Faculty Collection
UMBC Student Collection

Author/Creator

Author/Creator ORCID

Date

2020-04-07

Type of Work

journal articles preprints
Text

Department

Program

Citation of Original Publication

Ashwinkumar Ganesan etal., Locality Preserving Loss to Align Vector Spaces, 2020, https://arxiv.org/abs/2004.03734

Rights

This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.

Subjects

Abstract

We present a locality preserving loss (LPL)that improves the alignment between vector space representations (i.e., word or sentence embeddings) while separating (increasing distance between) uncorrelated representations as compared to the standard method that minimizes the mean squared error (MSE) only. The locality preserving loss optimizes the projection by maintaining the local neighborhood of embeddings that are found in the source, in the target domain as well. This reduces the overall size of the dataset required to the train model. We argue that vector space alignment (with MSE and LPL losses) acts as a regularizer in certain language-based classification tasks, leading to better accuracy than the base-line, especially when the size of the training set is small. We validate the effectiveness ofLPL on a cross-lingual word alignment task, a natural language inference task, and a multi-lingual inference task.