The Library
Characterizing the impact of geometric properties of word embeddings on task performance
Tools
Whitaker, Brendan, Newman-Griffis, Denis, Haldar, Aparajita, Ferhatosmanoglu, Hakan and Fosler-Lussier, Eric (2019) Characterizing the impact of geometric properties of word embeddings on task performance. In: 3rd Workshop on Evaluating Vector Space Representations for NLP, Minneapolis, USA, 6 Jun 2019. Published in: Proceedings of the 3rd Workshop on Evaluating Vector Space Representations for NLP pp. 8-17.
|
PDF
WRAP-characterizing-impact-geometric-word-embeddings-task-performance-Halder-2019.pdf - Published Version - Requires a PDF viewer. Available under License Creative Commons Attribution 4.0. Download (717Kb) | Preview |
Official URL: https://www.aclweb.org/anthology/W19-2002.pdf
Abstract
Analysis of word embedding properties to inform their use in downstream NLP tasks has largely been studied by assessing nearest neighbors. However, geometric properties of the continuous feature space contribute directly to the use of embedding features in downstream models, and are largely unexplored. We consider four properties of word embedding geometry, namely: position relative to the origin, distribution of features in the vector space, global pairwise distances, and local pairwise distances. We define a sequence of transformations to generate new embeddings that expose subsets of
these properties to downstream models and evaluate change in task performance to understand the contribution of each property to NLP
models. We transform publicly available pretrained embeddings from three popular toolkits (word2vec, GloVe, and FastText) and evaluate on a variety of intrinsic tasks, which model linguistic information in the vector space, and extrinsic tasks, which use vectors as input to
machine learning models. We find that intrinsic evaluations are highly sensitive to absolute position, while extrinsic tasks rely primarily
on local similarity. Our findings suggest that future embedding models and post-processing techniques should focus primarily on similarity to nearby points in vector space.
Item Type: | Conference Item (Paper) | |||||||||
---|---|---|---|---|---|---|---|---|---|---|
Subjects: | Q Science > QA Mathematics Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software |
|||||||||
Divisions: | Faculty of Science, Engineering and Medicine > Science > Computer Science | |||||||||
Library of Congress Subject Headings (LCSH): | Neural networks (Computer science) , Natural language processing (Computer science) , Embeddings (Mathematics) , Programming languages (Electronic computers) -- Semantics | |||||||||
Journal or Publication Title: | Proceedings of the 3rd Workshop on Evaluating Vector Space Representations for NLP | |||||||||
Publisher: | Association for Computational Linguistics | |||||||||
Official Date: | 6 June 2019 | |||||||||
Dates: |
|
|||||||||
Page Range: | pp. 8-17 | |||||||||
Status: | Peer Reviewed | |||||||||
Publication Status: | Published | |||||||||
Access rights to Published version: | Open Access (Creative Commons) | |||||||||
Date of first compliant deposit: | 22 April 2020 | |||||||||
Date of first compliant Open Access: | 22 April 2020 | |||||||||
RIOXX Funder/Project Grant: |
|
|||||||||
Conference Paper Type: | Paper | |||||||||
Title of Event: | 3rd Workshop on Evaluating Vector Space Representations for NLP | |||||||||
Type of Event: | Workshop | |||||||||
Location of Event: | Minneapolis, USA | |||||||||
Date(s) of Event: | 6 Jun 2019 |
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |
Downloads
Downloads per month over past year