Papers › Rotated Word Vector Representations and their Interpretability

Rotated Word Vector Representations and their Interpretability

1 Sep 2017EMNLP 2017 9archive 2025-07-28

Sungjoon Park, JinYeong Bak, Alice Oh

Vector representation of words improves performance in various NLP tasks, but the high dimensional word vectors are very difficult to interpret. We apply several rotation algorithms to the vector representation of words to improve the interpretability. Unlike previous approaches that induce sparsity, the rotated vectors are interpretable while preserving the expressive performance of the original vectors. Furthermore, any prebuilt word vector representation can be rotated for improved interpretability. We apply rotation to skipgrams and glove and compare the expressive power and interpretability with the original vectors and the sparse overcomplete vectors. The results show that the rotated vectors outperform the original and the sparse overcomplete vectors for interpretability and expressiveness tasks.

PaperPDFCode

Code

SungjoonPark/factor_rotation officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

GloVeInterpretability

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections