A Structured Self-attentive Sentence Embedding
Abstract
This paper proposes a new model for extracting an interpretable sentence embedding by introducing self-attention. Instead of using a vector, we use a 2-D matrix to represent the embedding, with each row of the matrix attending on a different part of the sentence. We also propose a self-attention mechanism and a special regularization term for the model. As a side effect, the embedding comes with an easy way of visualizing what specific parts of the sentence are encoded into the embedding. We evaluate our model on 3 different tasks: author profiling, sentiment classification, and textual entailment. Results show that our model yields a significant performance gain compared to other sentence embedding methods in all of the 3 tasks.
Cite
@article{arxiv.1703.03130,
title = {A Structured Self-attentive Sentence Embedding},
author = {Zhouhan Lin and Minwei Feng and Cicero Nogueira dos Santos and Mo Yu and Bing Xiang and Bowen Zhou and Yoshua Bengio},
journal= {arXiv preprint arXiv:1703.03130},
year = {2017}
}
Comments
15 pages with appendix, 7 figures, 4 tables. Conference paper in 5th International Conference on Learning Representations (ICLR 2017)