SOTAVerified

SWOW-8500: Word Association task for Intrinsic Evaluation of Word Embeddings

2019-06-01WS 2019Code Available0· sign in to hype

Avijit Thawani, Biplav Srivastava, Anil Singh

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

Downstream evaluation of pretrained word embeddings is expensive, more so for tasks where current state of the art models are very large architectures. Intrinsic evaluation using word similarity or analogy datasets, on the other hand, suffers from several disadvantages. We propose a novel intrinsic evaluation task employing large word association datasets (particularly the Small World of Words dataset). We observe correlations not just between performances on SWOW-8500 and previously proposed intrinsic tasks of word similarity prediction, but also with downstream tasks (eg. Text Classification and Natural Language Inference). Most importantly, we report better confidence intervals for scores on our word association task, with no fall in correlation with downstream performance.

Tasks

Reproductions