CLNov 23, 2017

SPINE: SParse Interpretable Neural Embeddings

arXiv:1711.08792v1140 citations
Originality Incremental advance
AI Analysis

This addresses the need for interpretable word embeddings in natural language processing, offering a practical improvement over widely used methods.

The paper tackled the problem of uninterpretable dense word embeddings by proposing SPINE, a method that generates sparse and interpretable word representations from existing embeddings like GloVe and word2vec, resulting in improved interpretability and outperforming existing embeddings on benchmark tasks.

Prediction without justification has limited utility. Much of the success of neural models can be attributed to their ability to learn rich, dense and expressive representations. While these representations capture the underlying complexity and latent trends in the data, they are far from being interpretable. We propose a novel variant of denoising k-sparse autoencoders that generates highly efficient and interpretable distributed word representations (word embeddings), beginning with existing word representations from state-of-the-art methods like GloVe and word2vec. Through large scale human evaluation, we report that our resulting word embedddings are much more interpretable than the original GloVe and word2vec embeddings. Moreover, our embeddings outperform existing popular word embeddings on a diverse suite of benchmark downstream tasks.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes