Locality Preserving Loss to Align Vector Spaces

Simple item page
dc.contributor.authorGanesan, Ashwinkumar
dc.contributor.authorFerraro, Frank
dc.contributor.authorOates, Tim
dc.date.accessioned2020-05-13T14:29:40Z
dc.date.available2020-05-13T14:29:40Z
dc.date.issued2020-04-07
dc.description.abstractWe 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.en_US
dc.description.urihttps://arxiv.org/abs/2004.03734en_US
dc.format.extent10 pagesen_US
dc.genrejournal articles preprintsen_US
dc.identifierdoi:10.13016/m26woa-g4my
dc.identifier.citationAshwinkumar Ganesan etal., Locality Preserving Loss to Align Vector Spaces, 2020, https://arxiv.org/abs/2004.03734en_US
dc.identifier.urihttp://hdl.handle.net/11603/18590
dc.language.isoen_USen_US
dc.relation.isAvailableAtThe University of Maryland, Baltimore County (UMBC)
dc.relation.ispartofUMBC Computer Science and Electrical Engineering Department Collection
dc.relation.ispartofUMBC Student Collection
dc.relation.ispartofUMBC Faculty Collection
dc.rightsThis 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.
dc.titleLocality Preserving Loss to Align Vector Spacesen_US
dc.typeTexten_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
2004.03734.pdf
Size:
545.12 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.56 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

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