Check the preview of 2nd version of this platform
being developed by the open MLCommons taskforce on automation and reproducibility
as a free, open-source and technology-agnostic on-prem platform.
SWOW-8500: Word Association task for Intrinsic Evaluation of Word Embeddings
lib:fc94517be9d1bf2e (v1.0.0)
Authors: Avijit Thawani,Biplav Srivastava,Anil Singh
Where published: WS 2019 6
Document: PDF DOI
Abstract URL: https://www.aclweb.org/anthology/W19-2006/
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.
Where published: WS 2019 6
Document: PDF DOI
Abstract URL: https://www.aclweb.org/anthology/W19-2006/
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.
Relevant initiatives
Related knowledge about this paper
Reproduced results (crowd-benchmarking and competitions)
Artifact and reproducibility checklists
- ACM/cTuning artifact appendix and reproducibility checklist
- NeurIPS reproducibility checklist
- SIGPLAN's checklist for empirical evaluation
- Collective Knowledge (organizing research projects based on FAIR principles)