SPINE: SParse Interpretable Neural Embeddings


  • Anant Subramanian Carnegie Mellon University
  • Danish Pruthi Carnegie Mellon University
  • Harsh Jhamtani Carnegie Mellon University
  • Taylor Berg-Kirkpatrick Carnegie Mellon University
  • Eduard Hovy Carnegie Mellon University


interpretability, representation learning, word embeddings, autoencoder


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.




How to Cite

Subramanian, A., Pruthi, D., Jhamtani, H., Berg-Kirkpatrick, T., & Hovy, E. (2018). SPINE: SParse Interpretable Neural Embeddings. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/11935



Main Track: NLP and Knowledge Representation