Characterizing the Impact of Geometric Properties of Word Embeddings on Task Performance

Autor: Eric Fosler-Lussier, Brendan Whitaker, Hakan Ferhatosmanoglu, Aparajita Haldar, Denis Newman-Griffis

Publikováno v: Whitaker, B, Newman-Griffis, D, Haldar, A, Ferhatosmanoglu, H & Fosler-Lussier, E 2019, Characterizing the Impact of Geometric Properties of Word Embeddings on Task Performance . in Proceedings of the 3rd Workshop on Evaluating Vector Space Representations for NLP . Minneapolis, USA, pp. 8-17, The Third Workshop on Evaluating Vector Space Representations for NLP, Minneapolis, United States, 6/06/19 . https://doi.org/10.18653/v1/W19-2002
Proceedings of the 3rd Workshop on Evaluating Vector Space Representations for NLP

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 featu

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3a50d8f510f6f13a88c6ab6a85ccec73
https://www.pure.ed.ac.uk/ws/files/353258464/Characterising_the_impact_WHITAKER_DOA29032019_VOR_CC_BY.pdf

Measuring Swampiness: Quantifying Chaos in Large Heterogeneous Data Repositories

Autor: Luann Jung, Brendan Whitaker, Kyle Chard, Aaron Elmore

Publikováno v: Aaron Elmore

As scientific data repositories and filesystems grow in size and complexity, they become increasingly disorganized. The coupling of massive quantities of data with poor organization makes it challenging for scientists to locate and utilize relevant d

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ea9aee522e709d332eaab9e697893add